Ornith AI
partialShows if the model has enough results for an index.Ornith-1.5-35B-A3B
Ornith-1.5-35B-A3B is a reasoning model from Ornith AI in the Ornith 1.5 family. 14 benchmarks count toward its score, in 3 categories.
IndexOverall score out of 100.Unranked
CoverageShare of the index weight with results.55%
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.262K
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
14 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. |
|---|---|---|---|---|---|---|
| Graduate-Level Google-Proof Q&A | Knowledge | 89.2% | 60.6 | — | — | David Rein et al. |
| GPQA Diamond | Knowledge | 89.2% | 60.6 | — | — | David Rein et al. |
| Software Engineering Benchmark Verified | Coding | 79.0% | 60.9 | — | — | Carlos E. Jimenez et al. |
| Claw-Eval | Agentic | 72.5% | 72.3 | — | — | Bowen Ye et al. |
| MCP Atlas | Agentic | 70.2% | 61.0 | — | — | OpenAI |
| Terminal-Bench 2.1 (provider run) | Agentic | 67.8% | 64.1 | — | — | DeepSeek-AI |
| WideResearch | Agentic | 67.8% | 52.6 | — | — | Qwen |
| Terminal-Bench 2.1 (provider run) | Agentic | 67.8% | 64.1 | — | — | DeepSeek-AI |
| BrowseComp | Agentic | 67.6% | 56.6 | — | — | OpenAI |
| SWE-bench Pro | Coding | 59.6% | 61.6 | — | — | Xiang Deng et al. |
| Toolathlon-Verified | Agentic | 48.7% | 50.8 | — | — | Moonshot AI |
| NL2Repo | Coding | 46.2% | 61.2 | — | — | MiniMax |
| Humanity's Last Exam with tools | Agentic | 33.4% | 47.0 | — | — | DeepSeek-AI |
| Humanity's Last Exam | Knowledge | 25.6% | 50.5 | — | — | Center for AI Safety et al. |
| Humanity's Last Exam without tools | Knowledge | 25.6% | 50.5 | — | — | OpenAI |
| DeepSWE | Agentic | 22.0% | 39.8 | — | — | Datacurve AI |
| Terminal-Bench 3.0 | Agentic | 5.1% | 58.8 | — | — | Ryan Marten et al. |
14 benchmarks count, from 17 of 17 results. A grey row does not count. Too few models took that benchmark.