boatbomber commited on
Commit
1ec3cbe
·
1 Parent(s): 7fd8268

Add Claude Opus 5.5, Claude Sonnet 5.5, GPT 6 Sol, Astra and Luna; update prices

Browse files
data/details/index.json CHANGED
@@ -1 +1 @@
1
- {"version":1,"generatedAt":"2026-09-07","models":[{"id":"qwen-2-5-coder-32b-q4-k-m","name":"Qwen 2.5 Coder 32B (Q4_K_M)","hasDetails":true},{"id":"qwen-3-4b-instruct-2507-q8-0","name":"Qwen 3 4B Instruct 2507 (Q8_0)","hasDetails":true},{"id":"qwen-3-coder-30b-a3b","name":"Qwen 3 Coder 30B-A3B","hasDetails":true},{"id":"qwen-3-5-9b","name":"Qwen 3.5 9B","hasDetails":true},{"id":"qwen-3-6-27b","name":"Qwen 3.6 27B","hasDetails":true},{"id":"qwen-3-6-35b-a3b","name":"Qwen 3.6 35B-A3B","hasDetails":true},{"id":"qwen-3-8-2-4t-a95b","name":"Qwen 3.8 2.4T-A95B","hasDetails":true},{"id":"qwen-3-8-27b-medium-q4-k-xl","name":"Qwen 3.8 27B (Medium, Q4_K_XL)","hasDetails":true},{"id":"qwen-3-8-27b-xhigh-q4-k-xl","name":"Qwen 3.8 27B (XHigh, Q4_K_XL)","hasDetails":true},{"id":"qwen-3-8-flash-next-medium-nvfp4","name":"Qwen 3.8 Flash Next (Medium, NVFP4)","hasDetails":true},{"id":"qwen-3-8-flash-next-xhigh-nvfp4","name":"Qwen 3.8 Flash Next (XHigh, NVFP4)","hasDetails":true},{"id":"claude-fable-5-medium","name":"Claude Fable 5 (Medium)","hasDetails":true},{"id":"claude-fable-5-1-medium","name":"Claude Fable 5.1 (Medium)","hasDetails":true},{"id":"claude-haiku-4-5-extended-thinking","name":"Claude Haiku 4.5 (Extended Thinking)","hasDetails":true},{"id":"claude-opus-4-8-medium","name":"Claude Opus 4.8 (Medium)","hasDetails":true},{"id":"claude-opus-5-medium","name":"Claude Opus 5 (Medium)","hasDetails":true},{"id":"claude-sonnet-4-medium","name":"Claude Sonnet 4 (Medium)","hasDetails":true},{"id":"claude-sonnet-5-medium","name":"Claude Sonnet 5 (Medium)","hasDetails":true},{"id":"deepseek-r1-0528","name":"Deepseek R1 0528","hasDetails":true},{"id":"deepseek-v4-flash","name":"Deepseek V4 Flash","hasDetails":true},{"id":"deepseek-v4-flash-0731","name":"Deepseek V4 Flash 0731","hasDetails":true},{"id":"deepseek-v4-pro-0813-high","name":"Deepseek V4 Pro 0813 (High)","hasDetails":true},{"id":"gemini-2-5-pro-medium","name":"Gemini 2.5 Pro (Medium)","hasDetails":true},{"id":"gemini-3-1-pro-medium","name":"Gemini 3.1 Pro (Medium)","hasDetails":true},{"id":"gemini-3-7-flash-medium","name":"Gemini 3.7 Flash (Medium)","hasDetails":true},{"id":"gemini-3-8-flash-high","name":"Gemini 3.8 Flash (High)","hasDetails":true},{"id":"gemma-3-27b","name":"Gemma 3 27B","hasDetails":true},{"id":"gemma-4-26b-a4b","name":"Gemma 4 26B-A4B","hasDetails":true},{"id":"gemma-4-31b","name":"Gemma 4 31B","hasDetails":true},{"id":"llama-3-1-8b-instruct","name":"Llama 3.1 8B Instruct","hasDetails":true},{"id":"muse-glimmer-30b-q4-k-xl","name":"Muse Glimmer 30B (Q4_K_XL)","hasDetails":true},{"id":"devstral-small-2507-q4-k-m","name":"Devstral Small 2507 (Q4_K_M)","hasDetails":true},{"id":"kimi-k3-high","name":"Kimi K3 (High)","hasDetails":true},{"id":"nemotron-3-5-lightning","name":"Nemotron 3.5 Lightning","hasDetails":true},{"id":"gpt-5-medium","name":"GPT 5 (Medium)","hasDetails":true},{"id":"gpt-5-4-nano-high","name":"GPT 5.4 nano (High)","hasDetails":true},{"id":"gpt-5-5-medium","name":"GPT 5.5 (Medium)","hasDetails":true},{"id":"gpt-5-6-luna-medium","name":"GPT 5.6 Luna (Medium)","hasDetails":true},{"id":"gpt-5-6-sol-medium","name":"GPT 5.6 Sol (Medium)","hasDetails":true},{"id":"gpt-5-6-terra-medium","name":"GPT 5.6 Terra (Medium)","hasDetails":true},{"id":"gpt-oss-20b","name":"GPT OSS 20B","hasDetails":true},{"id":"luau-devstral-24b-instruct-v0-2-q5-k-xl","name":"Luau Devstral 24B Instruct v0.2 (Q5_K_XL)","hasDetails":true},{"id":"luau-qwen3-4b-fim-v0-1-q8-0","name":"Luau Qwen3 4B FIM v0.1 (Q8_0)","hasDetails":true},{"id":"grok-4-5-medium","name":"Grok 4.5 (Medium)","hasDetails":true},{"id":"grok-4-6-medium","name":"Grok 4.6 (Medium)","hasDetails":true},{"id":"glm-4-7-flash","name":"GLM 4.7 Flash","hasDetails":true},{"id":"glm-5-2-high","name":"GLM 5.2 (High)","hasDetails":true},{"id":"glm-5-3-high","name":"GLM 5.3 (High)","hasDetails":true},{"id":"glm-5-3-flash-high","name":"GLM 5.3 Flash (High)","hasDetails":true}]}
 
1
+ {"version":1,"generatedAt":"2026-09-30","models":[{"id":"qwen-2-5-coder-32b-q4-k-m","name":"Qwen 2.5 Coder 32B (Q4_K_M)","hasDetails":true},{"id":"qwen-3-4b-instruct-2507-q8-0","name":"Qwen 3 4B Instruct 2507 (Q8_0)","hasDetails":true},{"id":"qwen-3-coder-30b-a3b","name":"Qwen 3 Coder 30B-A3B","hasDetails":true},{"id":"qwen-3-5-9b","name":"Qwen 3.5 9B","hasDetails":true},{"id":"qwen-3-6-27b","name":"Qwen 3.6 27B","hasDetails":true},{"id":"qwen-3-6-35b-a3b","name":"Qwen 3.6 35B-A3B","hasDetails":true},{"id":"qwen-3-8-2-4t-a95b","name":"Qwen 3.8 2.4T-A95B","hasDetails":true},{"id":"qwen-3-8-27b-medium-q4-k-xl","name":"Qwen 3.8 27B (Medium, Q4_K_XL)","hasDetails":true},{"id":"qwen-3-8-27b-xhigh-q4-k-xl","name":"Qwen 3.8 27B (XHigh, Q4_K_XL)","hasDetails":true},{"id":"qwen-3-8-flash-next-medium-nvfp4","name":"Qwen 3.8 Flash Next (Medium, NVFP4)","hasDetails":true},{"id":"qwen-3-8-flash-next-xhigh-nvfp4","name":"Qwen 3.8 Flash Next (XHigh, NVFP4)","hasDetails":true},{"id":"claude-fable-5-medium","name":"Claude Fable 5 (Medium)","hasDetails":true},{"id":"claude-fable-5-1-medium","name":"Claude Fable 5.1 (Medium)","hasDetails":true},{"id":"claude-haiku-4-5-extended-thinking","name":"Claude Haiku 4.5 (Extended Thinking)","hasDetails":true},{"id":"claude-opus-4-8-medium","name":"Claude Opus 4.8 (Medium)","hasDetails":true},{"id":"claude-opus-5-medium","name":"Claude Opus 5 (Medium)","hasDetails":true},{"id":"claude-opus-5-5-medium","name":"Claude Opus 5.5 (Medium)","hasDetails":true},{"id":"claude-sonnet-4-medium","name":"Claude Sonnet 4 (Medium)","hasDetails":true},{"id":"claude-sonnet-5-medium","name":"Claude Sonnet 5 (Medium)","hasDetails":true},{"id":"claude-sonnet-5-5-medium","name":"Claude Sonnet 5.5 (Medium)","hasDetails":true},{"id":"deepseek-r1-0528","name":"Deepseek R1 0528","hasDetails":true},{"id":"deepseek-v4-flash","name":"Deepseek V4 Flash","hasDetails":true},{"id":"deepseek-v4-flash-0731","name":"Deepseek V4 Flash 0731","hasDetails":true},{"id":"deepseek-v4-pro-0813-high","name":"Deepseek V4 Pro 0813 (High)","hasDetails":true},{"id":"gemini-2-5-pro-medium","name":"Gemini 2.5 Pro (Medium)","hasDetails":true},{"id":"gemini-3-1-pro-medium","name":"Gemini 3.1 Pro (Medium)","hasDetails":true},{"id":"gemini-3-7-flash-medium","name":"Gemini 3.7 Flash (Medium)","hasDetails":true},{"id":"gemini-3-8-flash-high","name":"Gemini 3.8 Flash (High)","hasDetails":true},{"id":"gemma-3-27b","name":"Gemma 3 27B","hasDetails":true},{"id":"gemma-4-26b-a4b","name":"Gemma 4 26B-A4B","hasDetails":true},{"id":"gemma-4-31b","name":"Gemma 4 31B","hasDetails":true},{"id":"llama-3-1-8b-instruct","name":"Llama 3.1 8B Instruct","hasDetails":true},{"id":"muse-glimmer-30b-q4-k-xl","name":"Muse Glimmer 30B (Q4_K_XL)","hasDetails":true},{"id":"devstral-small-2507-q4-k-m","name":"Devstral Small 2507 (Q4_K_M)","hasDetails":true},{"id":"kimi-k3-high","name":"Kimi K3 (High)","hasDetails":true},{"id":"nemotron-3-5-lightning","name":"Nemotron 3.5 Lightning","hasDetails":true},{"id":"gpt-5-medium","name":"GPT 5 (Medium)","hasDetails":true},{"id":"gpt-5-4-nano-high","name":"GPT 5.4 nano (High)","hasDetails":true},{"id":"gpt-5-5-medium","name":"GPT 5.5 (Medium)","hasDetails":true},{"id":"gpt-5-6-luna-medium","name":"GPT 5.6 Luna (Medium)","hasDetails":true},{"id":"gpt-5-6-sol-medium","name":"GPT 5.6 Sol (Medium)","hasDetails":true},{"id":"gpt-5-6-terra-medium","name":"GPT 5.6 Terra (Medium)","hasDetails":true},{"id":"gpt-6-astra-medium","name":"GPT 6 Astra (Medium)","hasDetails":true},{"id":"gpt-6-luna-medium","name":"GPT 6 Luna (Medium)","hasDetails":true},{"id":"gpt-6-sol-medium","name":"GPT 6 Sol (Medium)","hasDetails":true},{"id":"gpt-oss-20b","name":"GPT OSS 20B","hasDetails":true},{"id":"luau-devstral-24b-instruct-v0-2-q5-k-xl","name":"Luau Devstral 24B Instruct v0.2 (Q5_K_XL)","hasDetails":true},{"id":"luau-qwen3-4b-fim-v0-1-q8-0","name":"Luau Qwen3 4B FIM v0.1 (Q8_0)","hasDetails":true},{"id":"grok-4-5-medium","name":"Grok 4.5 (Medium)","hasDetails":true},{"id":"grok-4-6-medium","name":"Grok 4.6 (Medium)","hasDetails":true},{"id":"glm-4-7-flash","name":"GLM 4.7 Flash","hasDetails":true},{"id":"glm-5-2-high","name":"GLM 5.2 (High)","hasDetails":true},{"id":"glm-5-3-high","name":"GLM 5.3 (High)","hasDetails":true},{"id":"glm-5-3-flash-high","name":"GLM 5.3 Flash (High)","hasDetails":true}]}
data/details/models/claude-opus-5-5-medium.json ADDED
The diff for this file is too large to render. See raw diff
 
data/details/models/claude-sonnet-5-5-medium.json ADDED
The diff for this file is too large to render. See raw diff
 
data/details/models/gpt-6-astra-medium.json ADDED
The diff for this file is too large to render. See raw diff
 
data/details/models/gpt-6-luna-medium.json ADDED
The diff for this file is too large to render. See raw diff
 
data/details/models/gpt-6-sol-medium.json ADDED
The diff for this file is too large to render. See raw diff
 
data/details/outcomes.json CHANGED
The diff for this file is too large to render. See raw diff
 
data/leaderboard.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "generatedAt": "2026-09-07",
3
  "benchmarks": {
4
  "robloxqa": {
5
  "name": "RobloxQA v2.0",
@@ -197,8 +197,8 @@
197
  "releaseDate": "2025-07-31",
198
  "size": 61064245248,
199
  "price": {
200
- "input": 0.07,
201
- "output": 1.43
202
  },
203
  "scores": {
204
  "robloxqa": {
@@ -272,7 +272,7 @@
272
  "size": 19306216416,
273
  "price": {
274
  "input": 0.1,
275
- "output": 0.16949
276
  },
277
  "scores": {
278
  "robloxqa": {
@@ -345,8 +345,8 @@
345
  "releaseDate": "2026-04-22",
346
  "size": 55562855904,
347
  "price": {
348
- "input": 0.289,
349
- "output": 2.7573
350
  },
351
  "scores": {
352
  "robloxqa": {
@@ -419,8 +419,8 @@
419
  "releaseDate": "2026-04-16",
420
  "size": 71903645408,
421
  "price": {
422
- "input": 0.14,
423
- "output": 1.0747
424
  },
425
  "scores": {
426
  "robloxqa": {
@@ -724,7 +724,7 @@
724
  "size": 135195303851,
725
  "price": {
726
  "input": 0.15,
727
- "output": 0.46
728
  },
729
  "scores": {
730
  "robloxqa": {
@@ -798,7 +798,7 @@
798
  "size": 135195303851,
799
  "price": {
800
  "input": 0.15,
801
- "output": 0.46
802
  },
803
  "scores": {
804
  "robloxqa": {
@@ -1234,6 +1234,80 @@
1234
  }
1235
  }
1236
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1237
  {
1238
  "name": "Claude Sonnet 4 (Medium)",
1239
  "provider": "Anthropic",
@@ -1382,6 +1456,80 @@
1382
  }
1383
  }
1384
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1385
  {
1386
  "name": "Deepseek R1 0528",
1387
  "provider": "DeepSeek",
@@ -1464,7 +1612,7 @@
1464
  "size": 159609485896,
1465
  "price": {
1466
  "input": 0.098,
1467
- "output": 0.24458
1468
  },
1469
  "scores": {
1470
  "robloxqa": {
@@ -1537,8 +1685,8 @@
1537
  "releaseDate": "2026-07-31",
1538
  "size": 166878536440,
1539
  "price": {
1540
- "input": 0.14,
1541
- "output": 0.28
1542
  },
1543
  "scores": {
1544
  "robloxqa": {
@@ -1611,8 +1759,8 @@
1611
  "releaseDate": "2026-08-13",
1612
  "size": 892727580904,
1613
  "price": {
1614
- "input": 0.435,
1615
- "output": 0.9
1616
  },
1617
  "scores": {
1618
  "robloxqa": {
@@ -1760,7 +1908,7 @@
1760
  "size": null,
1761
  "price": {
1762
  "input": 2,
1763
- "output": 12.01
1764
  },
1765
  "scores": {
1766
  "robloxqa": {
@@ -1981,8 +2129,8 @@
1981
  "releaseDate": "2025-03-12",
1982
  "size": 54864813280,
1983
  "price": {
1984
- "input": 0.08,
1985
- "output": 0.37514
1986
  },
1987
  "scores": {
1988
  "robloxqa": {
@@ -2055,8 +2203,8 @@
2055
  "releaseDate": "2026-04-02",
2056
  "size": 51611872412,
2057
  "price": {
2058
- "input": 0.12,
2059
- "output": 0.3882
2060
  },
2061
  "scores": {
2062
  "robloxqa": {
@@ -2130,7 +2278,7 @@
2130
  "size": 62546177752,
2131
  "price": {
2132
  "input": 0.14,
2133
- "output": 0.4256
2134
  },
2135
  "scores": {
2136
  "robloxqa": {
@@ -2204,7 +2352,7 @@
2204
  "size": 16060522496,
2205
  "price": {
2206
  "input": 0.05,
2207
- "output": 0.071899
2208
  },
2209
  "scores": {
2210
  "robloxqa": {
@@ -2507,8 +2655,8 @@
2507
  "releaseDate": "2026-08-11",
2508
  "size": 65842365568,
2509
  "price": {
2510
- "input": 0.1,
2511
- "output": 0.25
2512
  },
2513
  "scores": {
2514
  "robloxqa": {
@@ -2656,7 +2804,7 @@
2656
  "size": null,
2657
  "price": {
2658
  "input": 0.2,
2659
- "output": 1.2471
2660
  },
2661
  "scores": {
2662
  "robloxqa": {
@@ -2877,8 +3025,8 @@
2877
  "releaseDate": "2026-07-09",
2878
  "size": null,
2879
  "price": {
2880
- "input": 5,
2881
- "output": 30
2882
  },
2883
  "scores": {
2884
  "robloxqa": {
@@ -3018,6 +3166,228 @@
3018
  }
3019
  }
3020
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3021
  {
3022
  "name": "GPT OSS 20B",
3023
  "provider": "OpenAI",
@@ -3026,7 +3396,7 @@
3026
  "size": 13761264768,
3027
  "price": {
3028
  "input": 0.03,
3029
- "output": 0.15499
3030
  },
3031
  "scores": {
3032
  "robloxqa": {
@@ -3256,7 +3626,7 @@
3256
  "size": null,
3257
  "price": {
3258
  "input": 2,
3259
- "output": 6.4831
3260
  },
3261
  "scores": {
3262
  "robloxqa": {
@@ -3330,7 +3700,7 @@
3330
  "size": null,
3331
  "price": {
3332
  "input": 2,
3333
- "output": 6.27
3334
  },
3335
  "scores": {
3336
  "robloxqa": {
@@ -3403,7 +3773,7 @@
3403
  "releaseDate": "2026-01-19",
3404
  "size": 31221488576,
3405
  "price": {
3406
- "input": 0.06,
3407
  "output": 0.4
3408
  },
3409
  "scores": {
@@ -3477,8 +3847,8 @@
3477
  "releaseDate": "2026-06-16",
3478
  "size": 1506659919872,
3479
  "price": {
3480
- "input": 0.826,
3481
- "output": 3.5017
3482
  },
3483
  "scores": {
3484
  "robloxqa": {
@@ -3551,8 +3921,8 @@
3551
  "releaseDate": "2026-08-18",
3552
  "size": 755632050320,
3553
  "price": {
3554
- "input": 1.12,
3555
- "output": 3.52
3556
  },
3557
  "scores": {
3558
  "robloxqa": {
@@ -3625,8 +3995,8 @@
3625
  "releaseDate": "2026-08-26",
3626
  "size": 328337455672,
3627
  "price": {
3628
- "input": 0.07125,
3629
- "output": 0.2375
3630
  },
3631
  "scores": {
3632
  "robloxqa": {
 
1
  {
2
+ "generatedAt": "2026-09-30",
3
  "benchmarks": {
4
  "robloxqa": {
5
  "name": "RobloxQA v2.0",
 
197
  "releaseDate": "2025-07-31",
198
  "size": 61064245248,
199
  "price": {
200
+ "input": 0.2925,
201
+ "output": 1.4625
202
  },
203
  "scores": {
204
  "robloxqa": {
 
272
  "size": 19306216416,
273
  "price": {
274
  "input": 0.1,
275
+ "output": 0.15
276
  },
277
  "scores": {
278
  "robloxqa": {
 
345
  "releaseDate": "2026-04-22",
346
  "size": 55562855904,
347
  "price": {
348
+ "input": 0.45,
349
+ "output": 2.7
350
  },
351
  "scores": {
352
  "robloxqa": {
 
419
  "releaseDate": "2026-04-16",
420
  "size": 71903645408,
421
  "price": {
422
+ "input": 0.15,
423
+ "output": 1
424
  },
425
  "scores": {
426
  "robloxqa": {
 
724
  "size": 135195303851,
725
  "price": {
726
  "input": 0.15,
727
+ "output": 0.47
728
  },
729
  "scores": {
730
  "robloxqa": {
 
798
  "size": 135195303851,
799
  "price": {
800
  "input": 0.15,
801
+ "output": 0.47
802
  },
803
  "scores": {
804
  "robloxqa": {
 
1234
  }
1235
  }
1236
  },
1237
+ {
1238
+ "name": "Claude Opus 5.5 (Medium)",
1239
+ "provider": "Anthropic",
1240
+ "url": "https://www.anthropic.com/claude/opus",
1241
+ "releaseDate": "2026-09-22",
1242
+ "size": null,
1243
+ "price": {
1244
+ "input": 4,
1245
+ "output": 20
1246
+ },
1247
+ "scores": {
1248
+ "robloxqa": {
1249
+ "freeform": {
1250
+ "correct": 2631,
1251
+ "noAnswer": 7,
1252
+ "inputTokens": 328040,
1253
+ "outputTokens": 804258
1254
+ },
1255
+ "multipleChoice": {
1256
+ "correct": 2957,
1257
+ "noAnswer": 6,
1258
+ "inputTokens": 600072,
1259
+ "outputTokens": 595864
1260
+ },
1261
+ "topics": {
1262
+ "classes": { "freeform": 1032, "multipleChoice": 1145 },
1263
+ "types": { "freeform": 285, "multipleChoice": 314 },
1264
+ "luau": { "freeform": 81, "multipleChoice": 85 },
1265
+ "scripting": { "freeform": 244, "multipleChoice": 275 },
1266
+ "gameplay": { "freeform": 108, "multipleChoice": 125 },
1267
+ "visuals": { "freeform": 102, "multipleChoice": 115 },
1268
+ "art": { "freeform": 119, "multipleChoice": 157 },
1269
+ "monetization": { "freeform": 152, "multipleChoice": 194 },
1270
+ "studio": { "freeform": 144, "multipleChoice": 163 },
1271
+ "learning": { "freeform": 364, "multipleChoice": 384 }
1272
+ }
1273
+ },
1274
+ "leetcode": {
1275
+ "easy": {
1276
+ "unitTestPassRate": 97.08,
1277
+ "fullPass": 44,
1278
+ "partialPass": 3,
1279
+ "fail": 0,
1280
+ "noCode": 0,
1281
+ "codeQuality": 99.9,
1282
+ "invalidSyntax": 0,
1283
+ "inputTokens": 27337,
1284
+ "outputTokens": 14874
1285
+ },
1286
+ "medium": {
1287
+ "unitTestPassRate": 98.6,
1288
+ "fullPass": 84,
1289
+ "partialPass": 13,
1290
+ "fail": 0,
1291
+ "noCode": 0,
1292
+ "codeQuality": 98.4,
1293
+ "invalidSyntax": 0,
1294
+ "inputTokens": 68437,
1295
+ "outputTokens": 83758
1296
+ },
1297
+ "hard": {
1298
+ "unitTestPassRate": 95.76,
1299
+ "fullPass": 53,
1300
+ "partialPass": 9,
1301
+ "fail": 2,
1302
+ "noCode": 0,
1303
+ "codeQuality": 97.6,
1304
+ "invalidSyntax": 0,
1305
+ "inputTokens": 43601,
1306
+ "outputTokens": 101476
1307
+ }
1308
+ }
1309
+ }
1310
+ },
1311
  {
1312
  "name": "Claude Sonnet 4 (Medium)",
1313
  "provider": "Anthropic",
 
1456
  }
1457
  }
1458
  },
1459
+ {
1460
+ "name": "Claude Sonnet 5.5 (Medium)",
1461
+ "provider": "Anthropic",
1462
+ "url": "https://www.anthropic.com/claude/sonnet",
1463
+ "releaseDate": "2026-09-28",
1464
+ "size": null,
1465
+ "price": {
1466
+ "input": 2,
1467
+ "output": 10
1468
+ },
1469
+ "scores": {
1470
+ "robloxqa": {
1471
+ "freeform": {
1472
+ "correct": 2358,
1473
+ "noAnswer": 1,
1474
+ "inputTokens": 328040,
1475
+ "outputTokens": 460606
1476
+ },
1477
+ "multipleChoice": {
1478
+ "correct": 2899,
1479
+ "noAnswer": 2,
1480
+ "inputTokens": 600072,
1481
+ "outputTokens": 562157
1482
+ },
1483
+ "topics": {
1484
+ "classes": { "freeform": 889, "multipleChoice": 1116 },
1485
+ "types": { "freeform": 263, "multipleChoice": 308 },
1486
+ "luau": { "freeform": 78, "multipleChoice": 84 },
1487
+ "scripting": { "freeform": 223, "multipleChoice": 276 },
1488
+ "gameplay": { "freeform": 95, "multipleChoice": 120 },
1489
+ "visuals": { "freeform": 97, "multipleChoice": 110 },
1490
+ "art": { "freeform": 112, "multipleChoice": 156 },
1491
+ "monetization": { "freeform": 126, "multipleChoice": 185 },
1492
+ "studio": { "freeform": 134, "multipleChoice": 161 },
1493
+ "learning": { "freeform": 341, "multipleChoice": 383 }
1494
+ }
1495
+ },
1496
+ "leetcode": {
1497
+ "easy": {
1498
+ "unitTestPassRate": 97.58,
1499
+ "fullPass": 44,
1500
+ "partialPass": 3,
1501
+ "fail": 0,
1502
+ "noCode": 0,
1503
+ "codeQuality": 100,
1504
+ "invalidSyntax": 0,
1505
+ "inputTokens": 27337,
1506
+ "outputTokens": 13076
1507
+ },
1508
+ "medium": {
1509
+ "unitTestPassRate": 97.58,
1510
+ "fullPass": 80,
1511
+ "partialPass": 16,
1512
+ "fail": 1,
1513
+ "noCode": 0,
1514
+ "codeQuality": 97.4,
1515
+ "invalidSyntax": 1,
1516
+ "inputTokens": 68437,
1517
+ "outputTokens": 76795
1518
+ },
1519
+ "hard": {
1520
+ "unitTestPassRate": 87.42,
1521
+ "fullPass": 44,
1522
+ "partialPass": 15,
1523
+ "fail": 5,
1524
+ "noCode": 0,
1525
+ "codeQuality": 92.9,
1526
+ "invalidSyntax": 1,
1527
+ "inputTokens": 43601,
1528
+ "outputTokens": 80778
1529
+ }
1530
+ }
1531
+ }
1532
+ },
1533
  {
1534
  "name": "Deepseek R1 0528",
1535
  "provider": "DeepSeek",
 
1612
  "size": 159609485896,
1613
  "price": {
1614
  "input": 0.098,
1615
+ "output": 0.28
1616
  },
1617
  "scores": {
1618
  "robloxqa": {
 
1685
  "releaseDate": "2026-07-31",
1686
  "size": 166878536440,
1687
  "price": {
1688
+ "input": 0.22,
1689
+ "output": 0.66
1690
  },
1691
  "scores": {
1692
  "robloxqa": {
 
1759
  "releaseDate": "2026-08-13",
1760
  "size": 892727580904,
1761
  "price": {
1762
+ "input": 0.66,
1763
+ "output": 1.98
1764
  },
1765
  "scores": {
1766
  "robloxqa": {
 
1908
  "size": null,
1909
  "price": {
1910
  "input": 2,
1911
+ "output": 12
1912
  },
1913
  "scores": {
1914
  "robloxqa": {
 
2129
  "releaseDate": "2025-03-12",
2130
  "size": 54864813280,
2131
  "price": {
2132
+ "input": 0.09,
2133
+ "output": 0.25
2134
  },
2135
  "scores": {
2136
  "robloxqa": {
 
2203
  "releaseDate": "2026-04-02",
2204
  "size": 51611872412,
2205
  "price": {
2206
+ "input": 0.13,
2207
+ "output": 0.4
2208
  },
2209
  "scores": {
2210
  "robloxqa": {
 
2278
  "size": 62546177752,
2279
  "price": {
2280
  "input": 0.14,
2281
+ "output": 0.4
2282
  },
2283
  "scores": {
2284
  "robloxqa": {
 
2352
  "size": 16060522496,
2353
  "price": {
2354
  "input": 0.05,
2355
+ "output": 0.08
2356
  },
2357
  "scores": {
2358
  "robloxqa": {
 
2655
  "releaseDate": "2026-08-11",
2656
  "size": 65842365568,
2657
  "price": {
2658
+ "input": 0.07,
2659
+ "output": 0.2
2660
  },
2661
  "scores": {
2662
  "robloxqa": {
 
2804
  "size": null,
2805
  "price": {
2806
  "input": 0.2,
2807
+ "output": 1.25
2808
  },
2809
  "scores": {
2810
  "robloxqa": {
 
3025
  "releaseDate": "2026-07-09",
3026
  "size": null,
3027
  "price": {
3028
+ "input": 2,
3029
+ "output": 10
3030
  },
3031
  "scores": {
3032
  "robloxqa": {
 
3166
  }
3167
  }
3168
  },
3169
+ {
3170
+ "name": "GPT 6 Astra (Medium)",
3171
+ "provider": "OpenAI",
3172
+ "url": "https://developers.openai.com/api/docs/models/gpt-6-astra",
3173
+ "releaseDate": "2026-09-04",
3174
+ "size": null,
3175
+ "price": {
3176
+ "input": 10,
3177
+ "output": 50
3178
+ },
3179
+ "scores": {
3180
+ "robloxqa": {
3181
+ "freeform": {
3182
+ "correct": 2614,
3183
+ "noAnswer": 0,
3184
+ "inputTokens": 225589,
3185
+ "outputTokens": 431945
3186
+ },
3187
+ "multipleChoice": {
3188
+ "correct": 2955,
3189
+ "noAnswer": 0,
3190
+ "inputTokens": 404067,
3191
+ "outputTokens": 128108
3192
+ },
3193
+ "topics": {
3194
+ "classes": { "freeform": 1032, "multipleChoice": 1137 },
3195
+ "types": { "freeform": 284, "multipleChoice": 313 },
3196
+ "luau": { "freeform": 81, "multipleChoice": 86 },
3197
+ "scripting": { "freeform": 244, "multipleChoice": 280 },
3198
+ "gameplay": { "freeform": 107, "multipleChoice": 124 },
3199
+ "visuals": { "freeform": 102, "multipleChoice": 115 },
3200
+ "art": { "freeform": 114, "multipleChoice": 159 },
3201
+ "monetization": { "freeform": 155, "multipleChoice": 194 },
3202
+ "studio": { "freeform": 145, "multipleChoice": 163 },
3203
+ "learning": { "freeform": 350, "multipleChoice": 384 }
3204
+ }
3205
+ },
3206
+ "leetcode": {
3207
+ "easy": {
3208
+ "unitTestPassRate": 97.51,
3209
+ "fullPass": 45,
3210
+ "partialPass": 2,
3211
+ "fail": 0,
3212
+ "noCode": 0,
3213
+ "codeQuality": 99.6,
3214
+ "invalidSyntax": 0,
3215
+ "inputTokens": 20113,
3216
+ "outputTokens": 7124
3217
+ },
3218
+ "medium": {
3219
+ "unitTestPassRate": 98.52,
3220
+ "fullPass": 83,
3221
+ "partialPass": 14,
3222
+ "fail": 0,
3223
+ "noCode": 0,
3224
+ "codeQuality": 99.2,
3225
+ "invalidSyntax": 0,
3226
+ "inputTokens": 49965,
3227
+ "outputTokens": 46488
3228
+ },
3229
+ "hard": {
3230
+ "unitTestPassRate": 94.88,
3231
+ "fullPass": 53,
3232
+ "partialPass": 9,
3233
+ "fail": 2,
3234
+ "noCode": 0,
3235
+ "codeQuality": 98.8,
3236
+ "invalidSyntax": 0,
3237
+ "inputTokens": 32013,
3238
+ "outputTokens": 60591
3239
+ }
3240
+ }
3241
+ }
3242
+ },
3243
+ {
3244
+ "name": "GPT 6 Luna (Medium)",
3245
+ "provider": "OpenAI",
3246
+ "url": "https://developers.openai.com/api/docs/models/gpt-6-luna",
3247
+ "releaseDate": "2026-09-22",
3248
+ "size": null,
3249
+ "price": {
3250
+ "input": 0.1,
3251
+ "output": 0.5
3252
+ },
3253
+ "scores": {
3254
+ "robloxqa": {
3255
+ "freeform": {
3256
+ "correct": 2372,
3257
+ "noAnswer": 0,
3258
+ "inputTokens": 225589,
3259
+ "outputTokens": 758949
3260
+ },
3261
+ "multipleChoice": {
3262
+ "correct": 2869,
3263
+ "noAnswer": 0,
3264
+ "inputTokens": 404067,
3265
+ "outputTokens": 361312
3266
+ },
3267
+ "topics": {
3268
+ "classes": { "freeform": 915, "multipleChoice": 1096 },
3269
+ "types": { "freeform": 249, "multipleChoice": 303 },
3270
+ "luau": { "freeform": 77, "multipleChoice": 85 },
3271
+ "scripting": { "freeform": 223, "multipleChoice": 274 },
3272
+ "gameplay": { "freeform": 95, "multipleChoice": 115 },
3273
+ "visuals": { "freeform": 88, "multipleChoice": 107 },
3274
+ "art": { "freeform": 115, "multipleChoice": 156 },
3275
+ "monetization": { "freeform": 134, "multipleChoice": 187 },
3276
+ "studio": { "freeform": 131, "multipleChoice": 164 },
3277
+ "learning": { "freeform": 345, "multipleChoice": 382 }
3278
+ }
3279
+ },
3280
+ "leetcode": {
3281
+ "easy": {
3282
+ "unitTestPassRate": 97.58,
3283
+ "fullPass": 44,
3284
+ "partialPass": 3,
3285
+ "fail": 0,
3286
+ "noCode": 0,
3287
+ "codeQuality": 99.6,
3288
+ "invalidSyntax": 0,
3289
+ "inputTokens": 20113,
3290
+ "outputTokens": 14162
3291
+ },
3292
+ "medium": {
3293
+ "unitTestPassRate": 98.05,
3294
+ "fullPass": 81,
3295
+ "partialPass": 16,
3296
+ "fail": 0,
3297
+ "noCode": 0,
3298
+ "codeQuality": 97.4,
3299
+ "invalidSyntax": 0,
3300
+ "inputTokens": 49965,
3301
+ "outputTokens": 109936
3302
+ },
3303
+ "hard": {
3304
+ "unitTestPassRate": 81.19,
3305
+ "fullPass": 43,
3306
+ "partialPass": 14,
3307
+ "fail": 7,
3308
+ "noCode": 0,
3309
+ "codeQuality": 91.7,
3310
+ "invalidSyntax": 1,
3311
+ "inputTokens": 32013,
3312
+ "outputTokens": 168405
3313
+ }
3314
+ }
3315
+ }
3316
+ },
3317
+ {
3318
+ "name": "GPT 6 Sol (Medium)",
3319
+ "provider": "OpenAI",
3320
+ "url": "https://developers.openai.com/api/docs/models/gpt-6-sol",
3321
+ "releaseDate": "2026-09-22",
3322
+ "size": null,
3323
+ "price": {
3324
+ "input": 2,
3325
+ "output": 10
3326
+ },
3327
+ "scores": {
3328
+ "robloxqa": {
3329
+ "freeform": {
3330
+ "correct": 2471,
3331
+ "noAnswer": 0,
3332
+ "inputTokens": 225589,
3333
+ "outputTokens": 456839
3334
+ },
3335
+ "multipleChoice": {
3336
+ "correct": 2935,
3337
+ "noAnswer": 0,
3338
+ "inputTokens": 404067,
3339
+ "outputTokens": 193089
3340
+ },
3341
+ "topics": {
3342
+ "classes": { "freeform": 943, "multipleChoice": 1132 },
3343
+ "types": { "freeform": 266, "multipleChoice": 311 },
3344
+ "luau": { "freeform": 77, "multipleChoice": 85 },
3345
+ "scripting": { "freeform": 229, "multipleChoice": 279 },
3346
+ "gameplay": { "freeform": 103, "multipleChoice": 120 },
3347
+ "visuals": { "freeform": 96, "multipleChoice": 113 },
3348
+ "art": { "freeform": 122, "multipleChoice": 158 },
3349
+ "monetization": { "freeform": 143, "multipleChoice": 191 },
3350
+ "studio": { "freeform": 144, "multipleChoice": 163 },
3351
+ "learning": { "freeform": 348, "multipleChoice": 383 }
3352
+ }
3353
+ },
3354
+ "leetcode": {
3355
+ "easy": {
3356
+ "unitTestPassRate": 97,
3357
+ "fullPass": 42,
3358
+ "partialPass": 5,
3359
+ "fail": 0,
3360
+ "noCode": 0,
3361
+ "codeQuality": 99.7,
3362
+ "invalidSyntax": 0,
3363
+ "inputTokens": 20113,
3364
+ "outputTokens": 8801
3365
+ },
3366
+ "medium": {
3367
+ "unitTestPassRate": 98.43,
3368
+ "fullPass": 80,
3369
+ "partialPass": 17,
3370
+ "fail": 0,
3371
+ "noCode": 0,
3372
+ "codeQuality": 97.8,
3373
+ "invalidSyntax": 0,
3374
+ "inputTokens": 49965,
3375
+ "outputTokens": 58239
3376
+ },
3377
+ "hard": {
3378
+ "unitTestPassRate": 94.14,
3379
+ "fullPass": 50,
3380
+ "partialPass": 12,
3381
+ "fail": 2,
3382
+ "noCode": 0,
3383
+ "codeQuality": 95.4,
3384
+ "invalidSyntax": 0,
3385
+ "inputTokens": 32013,
3386
+ "outputTokens": 79816
3387
+ }
3388
+ }
3389
+ }
3390
+ },
3391
  {
3392
  "name": "GPT OSS 20B",
3393
  "provider": "OpenAI",
 
3396
  "size": 13761264768,
3397
  "price": {
3398
  "input": 0.03,
3399
+ "output": 0.15
3400
  },
3401
  "scores": {
3402
  "robloxqa": {
 
3626
  "size": null,
3627
  "price": {
3628
  "input": 2,
3629
+ "output": 6
3630
  },
3631
  "scores": {
3632
  "robloxqa": {
 
3700
  "size": null,
3701
  "price": {
3702
  "input": 2,
3703
+ "output": 6
3704
  },
3705
  "scores": {
3706
  "robloxqa": {
 
3773
  "releaseDate": "2026-01-19",
3774
  "size": 31221488576,
3775
  "price": {
3776
+ "input": 0.06025,
3777
  "output": 0.4
3778
  },
3779
  "scores": {
 
3847
  "releaseDate": "2026-06-16",
3848
  "size": 1506659919872,
3849
  "price": {
3850
+ "input": 1.4,
3851
+ "output": 4.4
3852
  },
3853
  "scores": {
3854
  "robloxqa": {
 
3921
  "releaseDate": "2026-08-18",
3922
  "size": 755632050320,
3923
  "price": {
3924
+ "input": 1.4,
3925
+ "output": 4.4
3926
  },
3927
  "scores": {
3928
  "robloxqa": {
 
3995
  "releaseDate": "2026-08-26",
3996
  "size": 328337455672,
3997
  "price": {
3998
+ "input": 0.15,
3999
+ "output": 0.5
4000
  },
4001
  "scores": {
4002
  "robloxqa": {
data/models.json CHANGED
@@ -50,8 +50,8 @@
50
  "releaseDate": "2025-07-31",
51
  "size": 61064245248,
52
  "price": {
53
- "input": 0.07,
54
- "output": 1.43
55
  },
56
  "resultFiles": {
57
  "freeform": "qwen-qwen3-coder-30b-a3b-instruct_ff.json5",
@@ -67,7 +67,7 @@
67
  "size": 19306216416,
68
  "price": {
69
  "input": 0.1,
70
- "output": 0.16949
71
  },
72
  "resultFiles": {
73
  "freeform": "qwen-qwen3.5-9b_ff.json5",
@@ -82,8 +82,8 @@
82
  "releaseDate": "2026-04-22",
83
  "size": 55562855904,
84
  "price": {
85
- "input": 0.289,
86
- "output": 2.7573
87
  },
88
  "resultFiles": {
89
  "freeform": "qwen-qwen3.6-27b_ff.json5",
@@ -98,8 +98,8 @@
98
  "releaseDate": "2026-04-16",
99
  "size": 71903645408,
100
  "price": {
101
- "input": 0.14,
102
- "output": 1.0747
103
  },
104
  "resultFiles": {
105
  "freeform": "qwen3.6-35b-a3b-mtp_ff.json5",
@@ -175,7 +175,7 @@
175
  "size": 135195303851,
176
  "price": {
177
  "input": 0.15,
178
- "output": 0.46
179
  },
180
  "resultFiles": {
181
  "freeform": "Qwen3.8-Flash-Next_ff.json5",
@@ -191,7 +191,7 @@
191
  "size": 135195303851,
192
  "price": {
193
  "input": 0.15,
194
- "output": 0.46
195
  },
196
  "resultFiles": {
197
  "freeform": "Qwen3.8-Flash-Next_ff_effort-xhigh.json5",
@@ -335,7 +335,7 @@
335
  "size": 159609485896,
336
  "price": {
337
  "input": 0.098,
338
- "output": 0.24458
339
  },
340
  "resultFiles": {
341
  "freeform": "deepseek-deepseek-v4-flash_ff.json5",
@@ -350,8 +350,8 @@
350
  "releaseDate": "2026-07-31",
351
  "size": 166878536440,
352
  "price": {
353
- "input": 0.14,
354
- "output": 0.28
355
  },
356
  "resultFiles": {
357
  "freeform": "deepseek-deepseek-v4-flash-0731_ff_route-siliconflow-fp8_maxtok128000.json5",
@@ -366,8 +366,8 @@
366
  "releaseDate": "2026-08-13",
367
  "size": 892727580904,
368
  "price": {
369
- "input": 0.435,
370
- "output": 0.9
371
  },
372
  "resultFiles": {
373
  "freeform": "deepseek-deepseek-v4-pro-0813_ff_effort-high_route-deepseek.json5",
@@ -399,7 +399,7 @@
399
  "size": null,
400
  "price": {
401
  "input": 2,
402
- "output": 12.01
403
  },
404
  "resultFiles": {
405
  "freeform": "gemini-3.1-pro-preview_ff_effort-medium.json5",
@@ -446,8 +446,8 @@
446
  "releaseDate": "2025-03-12",
447
  "size": 54864813280,
448
  "price": {
449
- "input": 0.08,
450
- "output": 0.37514
451
  },
452
  "resultFiles": {
453
  "freeform": "google-gemma-3-27b-it_ff.json5",
@@ -462,8 +462,8 @@
462
  "releaseDate": "2026-04-02",
463
  "size": 51611872412,
464
  "price": {
465
- "input": 0.12,
466
- "output": 0.3882
467
  },
468
  "resultFiles": {
469
  "freeform": "google-gemma-4-26b-a4b-it_ff_route-novita-bf16.json5",
@@ -479,7 +479,7 @@
479
  "size": 62546177752,
480
  "price": {
481
  "input": 0.14,
482
- "output": 0.4256
483
  },
484
  "resultFiles": {
485
  "freeform": "google-gemma-4-31b-it_ff.json5",
@@ -495,7 +495,7 @@
495
  "size": 16060522496,
496
  "price": {
497
  "input": 0.05,
498
- "output": 0.071899
499
  },
500
  "resultFiles": {
501
  "freeform": "meta-llama-llama-3.1-8b-instruct_ff.json5",
@@ -570,8 +570,8 @@
570
  "releaseDate": "2026-08-11",
571
  "size": 65842365568,
572
  "price": {
573
- "input": 0.1,
574
- "output": 0.25
575
  },
576
  "resultFiles": {
577
  "freeform": "nvidia-nemotron-3.5-lightning_ff_route-coreweave-bf16.json5",
@@ -603,7 +603,7 @@
603
  "size": null,
604
  "price": {
605
  "input": 0.2,
606
- "output": 1.2471
607
  },
608
  "resultFiles": {
609
  "freeform": "gpt-5.4-nano_ff_effort-high.json5",
@@ -650,8 +650,8 @@
650
  "releaseDate": "2026-07-09",
651
  "size": null,
652
  "price": {
653
- "input": 5,
654
- "output": 30
655
  },
656
  "resultFiles": {
657
  "freeform": "gpt-5.6-sol_ff_effort-medium.json5",
@@ -683,7 +683,7 @@
683
  "size": 13761264768,
684
  "price": {
685
  "input": 0.03,
686
- "output": 0.15499
687
  },
688
  "resultFiles": {
689
  "freeform": "openai-gpt-oss-20b_ff.json5",
@@ -743,7 +743,7 @@
743
  "size": null,
744
  "price": {
745
  "input": 2,
746
- "output": 6.4831
747
  },
748
  "resultFiles": {
749
  "freeform": "x-ai-grok-4.5_ff_effort-medium.json5",
@@ -759,7 +759,7 @@
759
  "size": null,
760
  "price": {
761
  "input": 2,
762
- "output": 6.27
763
  },
764
  "resultFiles": {
765
  "freeform": "x-ai-grok-4.6_ff_effort-medium_route-xai-zdr.json5",
@@ -774,7 +774,7 @@
774
  "releaseDate": "2026-01-19",
775
  "size": 31221488576,
776
  "price": {
777
- "input": 0.06,
778
  "output": 0.4
779
  },
780
  "resultFiles": {
@@ -790,8 +790,8 @@
790
  "releaseDate": "2026-06-16",
791
  "size": 1506659919872,
792
  "price": {
793
- "input": 0.826,
794
- "output": 3.5017
795
  },
796
  "resultFiles": {
797
  "freeform": "z-ai-glm-5.2_ff_effort-high_route-baidu-fp8.json5",
@@ -806,8 +806,8 @@
806
  "releaseDate": "2026-08-18",
807
  "size": 755632050320,
808
  "price": {
809
- "input": 1.12,
810
- "output": 3.52
811
  },
812
  "resultFiles": {
813
  "freeform": "z-ai-glm-5.3_ff_effort-high.json5",
@@ -830,5 +830,85 @@
830
  "multipleChoice": "z-ai-glm-5.3-flash_mc_effort-high.json5",
831
  "leetcode": "z-ai-glm-5.3-flash_effort-high.json5"
832
  }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
833
  }
834
  ]
 
50
  "releaseDate": "2025-07-31",
51
  "size": 61064245248,
52
  "price": {
53
+ "input": 0.2925,
54
+ "output": 1.4625
55
  },
56
  "resultFiles": {
57
  "freeform": "qwen-qwen3-coder-30b-a3b-instruct_ff.json5",
 
67
  "size": 19306216416,
68
  "price": {
69
  "input": 0.1,
70
+ "output": 0.15
71
  },
72
  "resultFiles": {
73
  "freeform": "qwen-qwen3.5-9b_ff.json5",
 
82
  "releaseDate": "2026-04-22",
83
  "size": 55562855904,
84
  "price": {
85
+ "input": 0.45,
86
+ "output": 2.7
87
  },
88
  "resultFiles": {
89
  "freeform": "qwen-qwen3.6-27b_ff.json5",
 
98
  "releaseDate": "2026-04-16",
99
  "size": 71903645408,
100
  "price": {
101
+ "input": 0.15,
102
+ "output": 1
103
  },
104
  "resultFiles": {
105
  "freeform": "qwen3.6-35b-a3b-mtp_ff.json5",
 
175
  "size": 135195303851,
176
  "price": {
177
  "input": 0.15,
178
+ "output": 0.47
179
  },
180
  "resultFiles": {
181
  "freeform": "Qwen3.8-Flash-Next_ff.json5",
 
191
  "size": 135195303851,
192
  "price": {
193
  "input": 0.15,
194
+ "output": 0.47
195
  },
196
  "resultFiles": {
197
  "freeform": "Qwen3.8-Flash-Next_ff_effort-xhigh.json5",
 
335
  "size": 159609485896,
336
  "price": {
337
  "input": 0.098,
338
+ "output": 0.28
339
  },
340
  "resultFiles": {
341
  "freeform": "deepseek-deepseek-v4-flash_ff.json5",
 
350
  "releaseDate": "2026-07-31",
351
  "size": 166878536440,
352
  "price": {
353
+ "input": 0.22,
354
+ "output": 0.66
355
  },
356
  "resultFiles": {
357
  "freeform": "deepseek-deepseek-v4-flash-0731_ff_route-siliconflow-fp8_maxtok128000.json5",
 
366
  "releaseDate": "2026-08-13",
367
  "size": 892727580904,
368
  "price": {
369
+ "input": 0.66,
370
+ "output": 1.98
371
  },
372
  "resultFiles": {
373
  "freeform": "deepseek-deepseek-v4-pro-0813_ff_effort-high_route-deepseek.json5",
 
399
  "size": null,
400
  "price": {
401
  "input": 2,
402
+ "output": 12
403
  },
404
  "resultFiles": {
405
  "freeform": "gemini-3.1-pro-preview_ff_effort-medium.json5",
 
446
  "releaseDate": "2025-03-12",
447
  "size": 54864813280,
448
  "price": {
449
+ "input": 0.09,
450
+ "output": 0.25
451
  },
452
  "resultFiles": {
453
  "freeform": "google-gemma-3-27b-it_ff.json5",
 
462
  "releaseDate": "2026-04-02",
463
  "size": 51611872412,
464
  "price": {
465
+ "input": 0.13,
466
+ "output": 0.4
467
  },
468
  "resultFiles": {
469
  "freeform": "google-gemma-4-26b-a4b-it_ff_route-novita-bf16.json5",
 
479
  "size": 62546177752,
480
  "price": {
481
  "input": 0.14,
482
+ "output": 0.4
483
  },
484
  "resultFiles": {
485
  "freeform": "google-gemma-4-31b-it_ff.json5",
 
495
  "size": 16060522496,
496
  "price": {
497
  "input": 0.05,
498
+ "output": 0.08
499
  },
500
  "resultFiles": {
501
  "freeform": "meta-llama-llama-3.1-8b-instruct_ff.json5",
 
570
  "releaseDate": "2026-08-11",
571
  "size": 65842365568,
572
  "price": {
573
+ "input": 0.07,
574
+ "output": 0.2
575
  },
576
  "resultFiles": {
577
  "freeform": "nvidia-nemotron-3.5-lightning_ff_route-coreweave-bf16.json5",
 
603
  "size": null,
604
  "price": {
605
  "input": 0.2,
606
+ "output": 1.25
607
  },
608
  "resultFiles": {
609
  "freeform": "gpt-5.4-nano_ff_effort-high.json5",
 
650
  "releaseDate": "2026-07-09",
651
  "size": null,
652
  "price": {
653
+ "input": 2,
654
+ "output": 10
655
  },
656
  "resultFiles": {
657
  "freeform": "gpt-5.6-sol_ff_effort-medium.json5",
 
683
  "size": 13761264768,
684
  "price": {
685
  "input": 0.03,
686
+ "output": 0.15
687
  },
688
  "resultFiles": {
689
  "freeform": "openai-gpt-oss-20b_ff.json5",
 
743
  "size": null,
744
  "price": {
745
  "input": 2,
746
+ "output": 6
747
  },
748
  "resultFiles": {
749
  "freeform": "x-ai-grok-4.5_ff_effort-medium.json5",
 
759
  "size": null,
760
  "price": {
761
  "input": 2,
762
+ "output": 6
763
  },
764
  "resultFiles": {
765
  "freeform": "x-ai-grok-4.6_ff_effort-medium_route-xai-zdr.json5",
 
774
  "releaseDate": "2026-01-19",
775
  "size": 31221488576,
776
  "price": {
777
+ "input": 0.06025,
778
  "output": 0.4
779
  },
780
  "resultFiles": {
 
790
  "releaseDate": "2026-06-16",
791
  "size": 1506659919872,
792
  "price": {
793
+ "input": 1.4,
794
+ "output": 4.4
795
  },
796
  "resultFiles": {
797
  "freeform": "z-ai-glm-5.2_ff_effort-high_route-baidu-fp8.json5",
 
806
  "releaseDate": "2026-08-18",
807
  "size": 755632050320,
808
  "price": {
809
+ "input": 1.4,
810
+ "output": 4.4
811
  },
812
  "resultFiles": {
813
  "freeform": "z-ai-glm-5.3_ff_effort-high.json5",
 
830
  "multipleChoice": "z-ai-glm-5.3-flash_mc_effort-high.json5",
831
  "leetcode": "z-ai-glm-5.3-flash_effort-high.json5"
832
  }
833
+ },
834
+ {
835
+ "name": "GPT 6 Sol (Medium)",
836
+ "provider": "OpenAI",
837
+ "url": "https://developers.openai.com/api/docs/models/gpt-6-sol",
838
+ "releaseDate": "2026-09-22",
839
+ "size": null,
840
+ "price": {
841
+ "input": 2,
842
+ "output": 10
843
+ },
844
+ "resultFiles": {
845
+ "freeform": "gpt-6-sol_ff_effort-medium.json5",
846
+ "multipleChoice": "gpt-6-sol_mc_effort-medium.json5",
847
+ "leetcode": "gpt-6-sol_effort-medium.json5"
848
+ }
849
+ },
850
+ {
851
+ "name": "GPT 6 Astra (Medium)",
852
+ "provider": "OpenAI",
853
+ "url": "https://developers.openai.com/api/docs/models/gpt-6-astra",
854
+ "releaseDate": "2026-09-04",
855
+ "size": null,
856
+ "price": {
857
+ "input": 10,
858
+ "output": 50
859
+ },
860
+ "resultFiles": {
861
+ "freeform": "gpt-6-astra_ff_effort-medium.json5",
862
+ "multipleChoice": "gpt-6-astra_mc_effort-medium.json5",
863
+ "leetcode": "gpt-6-astra_effort-medium.json5"
864
+ }
865
+ },
866
+ {
867
+ "name": "Claude Sonnet 5.5 (Medium)",
868
+ "provider": "Anthropic",
869
+ "url": "https://www.anthropic.com/claude/sonnet",
870
+ "releaseDate": "2026-09-28",
871
+ "size": null,
872
+ "price": {
873
+ "input": 2,
874
+ "output": 10
875
+ },
876
+ "resultFiles": {
877
+ "freeform": "claude-sonnet-5-5_ff_effort-medium.json5",
878
+ "multipleChoice": "claude-sonnet-5-5_mc_effort-medium.json5",
879
+ "leetcode": "claude-sonnet-5-5_effort-medium.json5"
880
+ }
881
+ },
882
+ {
883
+ "name": "GPT 6 Luna (Medium)",
884
+ "provider": "OpenAI",
885
+ "url": "https://developers.openai.com/api/docs/models/gpt-6-luna",
886
+ "releaseDate": "2026-09-22",
887
+ "size": null,
888
+ "price": {
889
+ "input": 0.1,
890
+ "output": 0.5
891
+ },
892
+ "resultFiles": {
893
+ "freeform": "gpt-6-luna_ff_effort-medium.json5",
894
+ "multipleChoice": "gpt-6-luna_mc_effort-medium.json5",
895
+ "leetcode": "gpt-6-luna_effort-medium.json5"
896
+ }
897
+ },
898
+ {
899
+ "name": "Claude Opus 5.5 (Medium)",
900
+ "provider": "Anthropic",
901
+ "url": "https://www.anthropic.com/claude/opus",
902
+ "releaseDate": "2026-09-22",
903
+ "size": null,
904
+ "price": {
905
+ "input": 4,
906
+ "output": 20
907
+ },
908
+ "resultFiles": {
909
+ "freeform": "claude-opus-5-5_ff_effort-medium.json5",
910
+ "multipleChoice": "claude-opus-5-5_mc_effort-medium.json5",
911
+ "leetcode": "claude-opus-5-5_effort-medium.json5"
912
+ }
913
  }
914
  ]