Add version history; merge the v1.0 release card into this page
Browse files
README.md
CHANGED
|
@@ -100,6 +100,20 @@ Method and limitations:
|
|
| 100 |
|
| 101 |
See the [release post and protocol](https://machinefi.com/blog/trio-spark-v13-decisions) and [downloadable results](https://machinefi.com/spark/benchmarks/v13-launch-table-2026-10-15.json) for the complete published context.
|
| 102 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 103 |
## Limitations and intended use
|
| 104 |
|
| 105 |
v1.3 scores below v1.0 on MachineFi's internal GUI-action suite despite improving on the published text panel. Evaluate it on your own screens and actions before increasing automation. Latency depends on the request and workload; the evaluation table is not a latency guarantee.
|
|
|
|
| 100 |
|
| 101 |
See the [release post and protocol](https://machinefi.com/blog/trio-spark-v13-decisions) and [downloadable results](https://machinefi.com/spark/benchmarks/v13-launch-table-2026-10-15.json) for the complete published context.
|
| 102 |
|
| 103 |
+
## Version history
|
| 104 |
+
|
| 105 |
+
**v1.3 路 October 15, 2026 (current).** Updated text decisions; image and sampled-video behavior unchanged. Ten-task panel 90.9% (see above). Public model ID `trio-spark-v1.3`.
|
| 106 |
+
|
| 107 |
+
**v1.0 路 September 30, 2026.** First release, served as `trio-spark-preview` (the alias now routes to the current model). Launch evaluation on the production API: SST-2 92.89%, AG News 88.46%, PubMedQA 85.33%, TweetEval 80.58% ([launch post](https://machinefi.com/blog/trio-spark-decisions-single-pass)). Replayable demo runs from the [public demo repository](https://github.com/machinefi/trio-spark):
|
| 108 |
+
|
| 109 |
+
| Environment | Result |
|
| 110 |
+
| --- | --- |
|
| 111 |
+
| Autonomous drone | 65 s, 25 calls, 75.7 m flown, 0 collisions, course completed |
|
| 112 |
+
| Browser agent | 4.002 s, 3 calls, requested item selected, autonomous `DONE` |
|
| 113 |
+
| Robot arm | 13.68 s, 13 calls, physical success, 0 forbidden contacts |
|
| 114 |
+
|
| 115 |
+
These demos send structured environment signals to Spark; they do not claim direct control from raw pixels. The former `MachineFi/Trio-Spark-v1.0` card is merged into this page.
|
| 116 |
+
|
| 117 |
## Limitations and intended use
|
| 118 |
|
| 119 |
v1.3 scores below v1.0 on MachineFi's internal GUI-action suite despite improving on the published text panel. Evaluate it on your own screens and actions before increasing automation. Latency depends on the request and workload; the evaluation table is not a latency guarantee.
|