mistral-small-2503: benchmark scores, price and ranking

mistral-small-2503 from Mistral AI ranks #719 of 743 LLMs on the LLMs Tiger aggregate benchmark score (41.9), based on 5 benchmark results captured up to 2026-10-13.

Organisation: Mistral AI
Type: Open-weight / local model
Open weights: Yes
Released: 2025-03-17 (source: epoch)
Cheapest API price: $0.100 in / $0.300 out per million tokens (via azure_ai, observed 2026-10-13T20:47Z)
Aggregate rank: #719 of 743 (score 41.9)

Relative to other models, mistral-small-2503 is strongest on GPQA Diamond (#197 of 275) and weakest on CritPt (#109 of 115).

Across the 5 benchmarks where at least ten models are scored, mistral-small-2503 is in the top 10% on 0 and in the top half on 0.

Its cheapest listed input price, $0.100 per million tokens, is lower than that of 79% of the 427 models with a listed price.

mistral-small-2503 benchmark results

mistral-small-2503 benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
GPQA Diamond	47.5%	#197 of 275	Epoch AI Benchmarking Hub	2026-10-13
DTBench	58.6%	#108 of 146	Epoch AI Benchmarking Hub	2026-10-13
OTIS Mock AIME	5.8%	#155 of 189	Epoch AI Benchmarking Hub	2026-10-13
SciCode	26.5%	#94 of 106	Epoch AI Benchmarking Hub	2026-10-13
CritPt	0.0%	#109 of 115	Epoch AI Benchmarking Hub	2026-10-13

About mistral-small-2503

mistral-small-2503 is an open-weight model that can run on your own hardware from Mistral AI. It was released on 2025-03-17, according to Epoch AI. The cheapest API listing we track charges $0.100 per million input tokens and $0.300 per million output tokens, through azure_ai. We hold 5 benchmark results for it across 3 areas, and none is in the top tenth of its board.

Where mistral-small-2503 stands

On our aggregate score, mistral-small-2503 is #719 of 743 ranked models, in the lower half. Its score is 41.9; the scale is centred on 50, so it sits 8.1 points below the typical model. That beats 3% of the ranked field. Among the 44 ranked Mistral AI models it is #42. The next one up is Mistral-7B-Instruct-v0.3 at 41.9. The next one down is ministral-3b-2410 at 41.3.

mistral-small-2503, benchmark by benchmark

mistral-small-2503 lands below the middle on GPQA Diamond: 47.5%, #197 of 275, with 71% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is Magistral Small 1.2 at 47.6%. It covers expert-level science questions. The board median is 71.7%, so mistral-small-2503 is 24.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

mistral-small-2503 lands below the middle on DTBench: 58.6%, #108 of 146, with 73% of the field scoring higher. Claude Opus 5.5 (max) leads at 98.9%; the closest result above is gemini-1.5-pro-002 at 59.0%. It covers dynamic tool-use benchmark. The board median is 68.8%, so mistral-small-2503 is 10.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

OTIS Mock AIME is a weak spot. mistral-small-2503 scores 5.8%, #155 of 189, behind 81% of the models measured. The leader, Claude Fable 5.1 (max), reaches 100.0%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so mistral-small-2503 is 51.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

SciCode is a weak spot. mistral-small-2503 scores 26.5%, #94 of 106, behind 88% of the models measured. The leader, Claude Opus 5.5 (max), reaches 66.9%. It covers scientific research code. The board median is 44.3%, so mistral-small-2503 is 17.8 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

CritPt is a weak spot. mistral-small-2503 scores 0.0%, #109 of 115, behind 94% of the models measured. The leader, GPT-5.6 Sol (max), reaches 32.3%. It covers unpublished research-level physics problems. The board median is 2.9%, so mistral-small-2503 is 2.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

Reasoning, maths and science: weak, ahead of 17% of the field on average across 3 benchmarks. Its best board here is GPQA Diamond (#197 of 275) and its weakest is CritPt (#109 of 115).

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so mistral-small-2503 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 Meta-Llama-3-70B-Instruct ($0.120) and qwen2.5-72b-instruct ($0.120).

Release history

The Mistral AI model released before it was mistral-small-3-2501 on 2025-01-30, which scores 45.0. The next one was mistral-small-3.1-2503 on 2025-03-17, at 44.4.

Reading these numbers

The 5 scores on this page come from 1 source: Epoch AI Benchmarking Hub (5). No official leaderboard supplied any of them, so treat them as third-party measurements. With 5 results the aggregate rank can move a lot when one new score arrives.