Mistral-7B-Instruct-v0.3: benchmark scores, price and ranking

Mistral-7B-Instruct-v0.3 from Mistral AI ranks #718 of 743 LLMs on the LLMs Tiger aggregate benchmark score (41.9), based on 3 benchmark results captured up to 2026-10-13.

Organisation: Mistral AI
Type: Open-weight / local model
Open weights: Yes
Released: 2024-05-27 (source: epoch)
Cheapest API price: $0.100 in / $0.100 out per million tokens (via ovhcloud, observed 2026-10-13T20:47Z)
Aggregate rank: #718 of 743 (score 41.9)

Relative to other models, Mistral-7B-Instruct-v0.3 is strongest on Chess Puzzles (#117 of 122) and weakest on OTIS Mock AIME (#188 of 189).

Across the 3 benchmarks where at least ten models are scored, Mistral-7B-Instruct-v0.3 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-7B-Instruct-v0.3 benchmark results

Mistral-7B-Instruct-v0.3 benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
Chess Puzzles	0.0%	#117 of 122	Epoch AI Benchmarking Hub	2026-10-13
GPQA Diamond	15.2%	#271 of 275	Epoch AI Benchmarking Hub	2026-10-13
OTIS Mock AIME	0.3%	#188 of 189	Epoch AI Benchmarking Hub	2026-10-13

About Mistral-7B-Instruct-v0.3

Mistral-7B-Instruct-v0.3 is an open-weight model that can run on your own hardware from Mistral AI. It was released on 2024-05-27, according to Epoch AI. The cheapest API listing we track charges $0.100 per million input tokens and $0.100 per million output tokens, through ovhcloud. We hold 3 benchmark results for it across 2 areas, and none is in the top tenth of its board.

Where Mistral-7B-Instruct-v0.3 stands

On our aggregate score, Mistral-7B-Instruct-v0.3 is #718 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 #41. The next one up is ministral-8b-2410 at 42.6. The next one down is mistral-small-2503 at 41.9.

Mistral-7B-Instruct-v0.3, benchmark by benchmark

Chess Puzzles is a weak spot. Mistral-7B-Instruct-v0.3 scores 0.0%, #117 of 122, behind 95% of the models measured. The leader, GPT-6 Astra (max), reaches 72.0%. It covers chess tactics puzzles. The board median is 12.5%, so Mistral-7B-Instruct-v0.3 is 12.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

GPQA Diamond is a weak spot. Mistral-7B-Instruct-v0.3 scores 15.2%, #271 of 275, behind 98% of the models measured. The leader, GPT-6 Astra (max), reaches 95.8%. It covers expert-level science questions. The board median is 71.7%, so Mistral-7B-Instruct-v0.3 is 56.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

OTIS Mock AIME is a weak spot. Mistral-7B-Instruct-v0.3 scores 0.3%, #188 of 189, behind 99% 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-7B-Instruct-v0.3 is 57.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

Reasoning, maths and science: weak, ahead of 1% of the field on average across 2 benchmarks. Its best board here is GPQA Diamond (#271 of 275) and its weakest is OTIS Mock AIME (#188 of 189).

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so Mistral-7B-Instruct-v0.3 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 open-mixtral-8x22b on 2024-04-17, which scores 46.0. The next one was Mistral-Nemo-Instruct-2407 on 2024-07-18, at 45.2.

Reading these numbers

The 3 scores on this page come from 1 source: Epoch AI Benchmarking Hub (3). No official leaderboard supplied any of them, so treat them as third-party measurements. With 3 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#715 SmolLM2-360M (42.0)
#716 gemini-1.5-flash-8b-001 (42.0)
#717 Llama 4 Maverick (42.0)
#719 mistral-small-2503 (41.9)
#720 claude-3-sonnet-20240229 (41.9)
#721 Phi-4-mini-instruct (41.8)