Darwin-31B-Opus: benchmark scores, price and ranking
Darwin-31B-Opus from FINAL-Bench ranks #123 of 743 LLMs on the LLMs Tiger aggregate benchmark score (51.4), based on 1 benchmark results captured up to 2026-10-13.
- Organisation
- FINAL-Bench
- Type
- Open-weight / local model
- Open weights
- Yes
- Aggregate rank
- #123 of 743 (score 51.4)
Across the 1 benchmark where at least ten models are scored, Darwin-31B-Opus is in the top 10% on 0 and in the top half on 1.
Darwin-31B-Opus benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| GPQA Diamond | 85.9% | #73 of 275 | HuggingFace GPQA Diamond leaderboard | 2026-10-13 |
About Darwin-31B-Opus
Darwin-31B-Opus is an open-weight model that can run on your own hardware from FINAL-Bench. No API price is listed for it yet. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.
Where Darwin-31B-Opus stands
On our aggregate score, Darwin-31B-Opus is #123 of 743 ranked models, in the top quarter. Its score is 51.4; the scale is centred on 50, so it sits 1.4 points above the typical model. That beats 83% of the ranked field. Among the 8 ranked FINAL-Bench models it is #6. The next one up is Darwin-27B-Opus at 51.5. The next one down is Darwin-4B-David at 51.3.
Darwin-31B-Opus, benchmark by benchmark
GPQA Diamond puts Darwin-31B-Opus at 85.9%, #73 of 275. That beats 73% of the models tested, but 9.9 points short of GPT-6 Astra (max) (95.8%). The results either side are Qwen3.6 35B-A3B (86.0%) and Claude Fable 5 (max) (85.9%). It covers expert-level science questions. The board median is 71.7%, so Darwin-31B-Opus is 14.2 points above it. Source: HuggingFace GPQA Diamond leaderboard, captured 2026-10-13.
Reading these numbers
The 1 score on this page comes from 1 source: HuggingFace GPQA Diamond leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 1 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #120 Gemini 3 Flash (51.5)
- #121 Claude Opus 4.6 (120K, High) (51.5)
- #122 Qwen3 235B A22B diff, no think, Alibaba API (51.5)
- #124 Claude Opus 4.6 (120K, Max) (51.4)
- #125 A.X-K2 (51.4)
- #126 GLM-5-FP8 (51.4)
More from FINAL-Bench
- Darwin-180B-RSI (#70, 52.3)
- Darwin-397B-ZTC (#73, 52.2)
- Darwin-398B-JGOS (#86, 52.0)
- Darwin-36B-Opus (#103, 51.7)
- Darwin-27B-Opus (#112, 51.5)
- Darwin-4B-David (#129, 51.3)
Compare it on the live leaderboard → · How the aggregate score works