Shanghai Artificial Intelligence Laboratory
partialShows if the model has enough results for an index.Atria Dawn Preview
Atria Dawn Preview is a reasoning model from Shanghai Artificial Intelligence Laboratory in the Atria Dawn family. 10 benchmarks count toward its score, in 2 categories.
IndexOverall score out of 100.Unranked
CoverageShare of the index weight with results.40%
SpeedOutput tokens per second.—
Input / 1MUS dollars per 1M input tokens.Free
Output / 1MUS dollars per 1M output tokens.Free
ContextMaximum tokens in one request.256K
EloLMArena rating and rank.N/A
The index is a score out of 100. The ± range shows how much it can change.
CapabilitiesScore per category, out of 100.
Out of 100Results
10 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result as a score out of 100. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| DeepSearchQA | Agentic | 96.0% | 74.4 | — | — | Meta AI |
| BrowseComp | Agentic | 92.5% | 77.4 | — | — | OpenAI |
| CyberGym | Agentic | 86.5% | 75.3 | — | — | Zhun Wang et al. |
| MLE-Bench Lite | Agentic | 86.2% | — | — | — | MiniMax |
| WideResearch | Agentic | 81.9% | 67.9 | — | — | Qwen |
| Terminal-Bench 2.1 (provider run) | Agentic | 78.3% | 70.3 | — | — | DeepSeek-AI |
| Terminal-Bench 2.1 (provider run) | Agentic | 78.3% | 70.3 | — | — | DeepSeek-AI |
| Berkeley Function Calling Leaderboard v4 | Agentic | 77.0% | 62.1 | — | — | Arcee AI |
| SWE-bench Pro | Coding | 59.6% | 61.6 | — | — | Xiang Deng et al. |
| AutomationBench | Agentic | 53.8% | 95.0 | — | — | Moonshot AI |
| JobBench | Agentic | 50.3% | 68.7 | — | — | Yuetai Li et al. |
| τ³-Bench Tool-Agent-User Evaluation | Agentic | 41.2% | 30.2 | — | — | Sierra Research |
10 benchmarks count, from 11 of 12 results. A grey row does not count. Too few models took that benchmark.