Mistral-Small-4-119B-2603: benchmark scores, price and ranking
Mistral-Small-4-119B-2603 from mistralai ranks #226 of 743 LLMs on the LLMs Tiger aggregate benchmark score (49.9), based on 1 benchmark results captured up to 2026-10-13.
- Organisation
- mistralai
- Type
- Open-weight / local model
- Open weights
- Yes
- Aggregate rank
- #226 of 743 (score 49.9)
Across the 1 benchmark where at least ten models are scored, Mistral-Small-4-119B-2603 is in the top 10% on 0 and in the top half on 0.
Mistral-Small-4-119B-2603 benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| GPQA Diamond | 71.2% | #143 of 275 | HuggingFace GPQA Diamond leaderboard | 2026-10-13 |
About Mistral-Small-4-119B-2603
Mistral-Small-4-119B-2603 is an open-weight model that can run on your own hardware from mistralai. 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 Mistral-Small-4-119B-2603 stands
On our aggregate score, Mistral-Small-4-119B-2603 is #226 of 743 ranked models, around the middle of the table. Its score is 49.9; the scale is centred on 50, so it sits 0.1 points below the typical model. That beats 70% of the ranked field. Among the 10 ranked mistralai models it is #1. The next one down is Mistral-Large-Instruct-2411 at 49.6.
Mistral-Small-4-119B-2603, benchmark by benchmark
Mistral-Small-4-119B-2603 lands below the middle on GPQA Diamond: 71.2%, #143 of 275, with 52% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is deepseek-chat at 71.2%. It covers expert-level science questions. The board median is 71.7%, so Mistral-Small-4-119B-2603 is 0.5 points below 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
- #223 DeepSeek v4 (unknown) (50.0)
- #224 Devstral Small (2512) (49.9)
- #225 claude-sonnet-4-20250514_32K (49.9)
- #227 DeepSeek Coder V2 0724 (49.9)
- #228 MiniMax-M2.1 (49.9)
- #229 claude-sonnet-4-20250514_12K (49.9)
More from mistralai
- Mistral-Large-Instruct-2411 (#254, 49.6)
- Mistral-Large-Instruct-2407 (#280, 49.3)
- Mistral-Small-24B-Base-2501 (#408, 47.7)
- Mistral-Small-Instruct-2409 (#474, 46.9)
- Mathstral-7B-v0.1 (#540, 46.1)
- Mixtral-8x7B-v0.1 (#550, 45.9)
Compare it on the live leaderboard → · How the aggregate score works