LLMs TigerLive LLM benchmarks

mistral-medium-2505: benchmark scores, price and ranking

mistral-medium-2505 from Mistral AI ranks #591 of 743 LLMs on the LLMs Tiger aggregate benchmark score (45.4), based on 4 benchmark results captured up to 2026-10-13.

Organisation
Mistral AI
Type
Frontier model
Open weights
No
Released
2025-05-07 (source: epoch)
Cheapest API price
$0.400 in / $2.00 out per million tokens (via azure_ai, observed 2026-10-13T20:47Z)
Aggregate rank
#591 of 743 (score 45.4)

Relative to other models, mistral-medium-2505 is strongest on GPQA Diamond (#167 of 275) and weakest on Humanity's Last Exam (#23 of 27).

Across the 4 benchmarks where at least ten models are scored, mistral-medium-2505 is in the top 10% on 0 and in the top half on 0.

Its cheapest listed input price, $0.400 per million tokens, is lower than that of 53% of the 427 models with a listed price.

mistral-medium-2505 benchmark results

mistral-medium-2505 benchmark scores, ranked against all models measured on each benchmark
BenchmarkScoreRankSourceCaptured
GPQA Diamond59.5%#167 of 275Epoch AI Benchmarking Hub2026-10-13
OTIS Mock AIME32.2%#118 of 189Epoch AI Benchmarking Hub2026-10-13
DTBench62.3%#93 of 146Epoch AI Benchmarking Hub2026-10-13
Humanity's Last Exam4.5%#23 of 27Epoch AI Benchmarking Hub2026-10-13

About mistral-medium-2505

mistral-medium-2505 is a frontier model from Mistral AI. It was released on 2025-05-07, according to Epoch AI. The cheapest API listing we track charges $0.400 per million input tokens and $2.00 per million output tokens, through azure_ai. We hold 4 benchmark results for it across 2 areas, and none is in the top tenth of its board.

Where mistral-medium-2505 stands

On our aggregate score, mistral-medium-2505 is #591 of 743 ranked models, in the lower half. Its score is 45.4; the scale is centred on 50, so it sits 4.6 points below the typical model. That beats 20% of the ranked field. Among the 44 ranked Mistral AI models it is #25. The next one up is mistral-large-2411 at 45.6. The next one down is Devstral Small 2 at 45.4.

mistral-medium-2505, benchmark by benchmark

mistral-medium-2505 lands below the middle on GPQA Diamond: 59.5%, #167 of 275, with 60% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is claude-haiku-4-5-20251001 at 60.5%. It covers expert-level science questions. The board median is 71.7%, so mistral-medium-2505 is 12.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

mistral-medium-2505 lands below the middle on OTIS Mock AIME: 32.2%, #118 of 189, with 62% of the field scoring higher. Claude Fable 5.1 (max) leads at 100.0%; the closest result above is claude-haiku-4-5-20251001 at 35.8%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so mistral-medium-2505 is 25.6 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

mistral-medium-2505 lands below the middle on DTBench: 62.3%, #93 of 146, with 63% of the field scoring higher. Claude Opus 5.5 (max) leads at 98.9%; the closest result above is GPT-5 nano (high) at 62.7%. It covers dynamic tool-use benchmark. The board median is 68.8%, so mistral-medium-2505 is 6.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Humanity's Last Exam is a weak spot. mistral-medium-2505 scores 4.5%, #23 of 27, behind 81% of the models measured. The leader, Muse Spark, reaches 40.6%. It covers expert-level questions across domains. The board median is 10.7%, so mistral-medium-2505 is 6.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

Reasoning, maths and science: uneven, ahead of 31% of the field on average across 3 benchmarks. Its best board here is GPQA Diamond (#167 of 275) and its weakest is Humanity's Last Exam (#23 of 27).

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so mistral-medium-2505 costs less than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on GLM-4.6 ($0.450) and WizardLM-2-8x22B ($0.480).

Release history

The Mistral AI model released before it was mistral-small-3.1-2503 on 2025-03-17, which scores 44.4. The next one was magistral-small-2506 on 2025-06-10, at 47.0.

Reading these numbers

The 4 scores on this page come from 1 source: Epoch AI Benchmarking Hub (4). No official leaderboard supplied any of them, so treat them as third-party measurements. With 4 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

More from Mistral AI

Compare it on the live leaderboard → · How the aggregate score works