magistral-small-2506: benchmark scores, price and ranking
magistral-small-2506 from Mistral AI ranks #472 of 743 LLMs on the LLMs Tiger aggregate benchmark score (47.0), based on 2 benchmark results captured up to 2026-10-13.
- Organisation
- Mistral AI
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2025-06-10 (source: epoch)
- Aggregate rank
- #472 of 743 (score 47.0)
Across the 2 benchmarks where at least ten models are scored, magistral-small-2506 is in the top 10% on 0 and in the top half on 0.
magistral-small-2506 benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| GPQA Diamond | 56.1% | #174 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| OTIS Mock AIME | 30.0% | #122 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
About magistral-small-2506
magistral-small-2506 is an open-weight model that can run on your own hardware from Mistral AI. It was released on 2025-06-10, according to Epoch AI. No API price is listed for it yet. We hold 2 benchmark results for it across 1 area, and none is in the top tenth of its board.
Where magistral-small-2506 stands
On our aggregate score, magistral-small-2506 is #472 of 743 ranked models, in the lower half. Its score is 47.0; the scale is centred on 50, so it sits 3.0 points below the typical model. That beats 36% of the ranked field. Among the 44 ranked Mistral AI models it is #12. The next one up is Magistral Medium 1.2 at 47.1. The next one down is codestral-2508 at 46.8.
magistral-small-2506, benchmark by benchmark
magistral-small-2506 lands below the middle on GPQA Diamond: 56.1%, #174 of 275, with 63% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is qwen-max-2025-01-25 at 56.1%. It covers expert-level science questions. The board median is 71.7%, so magistral-small-2506 is 15.7 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
magistral-small-2506 lands below the middle on OTIS Mock AIME: 30.0%, #122 of 189, with 64% of the field scoring higher. Claude Fable 5.1 (max) leads at 100.0%; the closest result above is mistral-small-3.2-2506 at 30.3%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so magistral-small-2506 is 27.8 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: uneven, ahead of 36% of the field on average across 2 benchmarks. Its best board here is GPQA Diamond (#174 of 275) and its weakest is OTIS Mock AIME (#122 of 189).
Release history
The Mistral AI model released before it was mistral-medium-2505 on 2025-05-07, which scores 45.4. The next one was Mistral Small 3.2 on 2025-06-20, at 44.0.
Reading these numbers
The 2 scores on this page come from 1 source: Epoch AI Benchmarking Hub (2). No official leaderboard supplied any of them, so treat them as third-party measurements. With 2 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #469 Step 3.7 Flash (47.0)
- #470 DeepSeek-R1-Distill-Qwen-14B (47.0)
- #471 Reflection-70B (47.0)
- #473 nemotron-3-ultra (47.0)
- #474 Mistral-Small-Instruct-2409 (46.9)
- #475 Qwen3-32B (46.9)
More from Mistral AI
- Mistral Large 2 (2407) (#231, 49.9)
- codestral-2405 (#352, 48.4)
- pixtral-large-2411 (#360, 48.3)
- Codestral-22B-v0.1-Q4_K_M (#392, 48.0)
- codestral:22b-v0.1-q8_0 (#393, 48.0)
- Mistral Large 4 (high) (#411, 47.7)
Compare it on the live leaderboard → · How the aggregate score works