mistral-large-2407: benchmark scores, price and ranking

mistral-large-2407 from Mistral AI ranks #680 of 743 LLMs on the LLMs Tiger aggregate benchmark score (43.3), based on 4 benchmark results captured up to 2026-10-13.

Organisation: Mistral AI
Type: Frontier model
Open weights: No
Released: 2024-07-24 (source: epoch)
Context window: 131,072 tokens
Cheapest API price: $2.00 in / $6.00 out per million tokens (via azure_ai, observed 2026-10-13T20:47Z)
Aggregate rank: #680 of 743 (score 43.3)

Relative to other models, mistral-large-2407 is strongest on DTBench (#100 of 146) and weakest on SimpleBench (#55 of 61).

Across the 4 benchmarks where at least ten models are scored, mistral-large-2407 is in the top 10% on 0 and in the top half on 0.

Its cheapest listed input price, $2.00 per million tokens, is lower than that of 18% of the 427 models with a listed price.

mistral-large-2407 benchmark results

mistral-large-2407 benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
DTBench	61.2%	#100 of 146	Epoch AI Benchmarking Hub	2026-10-13
GPQA Diamond	49.0%	#190 of 275	Epoch AI Benchmarking Hub	2026-10-13
OTIS Mock AIME	8.5%	#140 of 189	Epoch AI Benchmarking Hub	2026-10-13
SimpleBench	22.5%	#55 of 61	Epoch AI Benchmarking Hub	2026-10-13

About mistral-large-2407

mistral-large-2407 is a frontier model from Mistral AI. It was released on 2024-07-24, according to Epoch AI. It accepts up to 131,072 tokens of input at once. The cheapest API listing we track charges $2.00 per million input tokens and $6.00 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-large-2407 stands

On our aggregate score, mistral-large-2407 is #680 of 743 ranked models, in the lower half. Its score is 43.3; the scale is centred on 50, so it sits 6.7 points below the typical model. That beats 8% of the ranked field. Among the 44 ranked Mistral AI models it is #36. The next one up is Mistral Medium 3.5 at 43.5. The next one down is open-mixtral-8x7b at 43.2.

mistral-large-2407, benchmark by benchmark

mistral-large-2407 lands below the middle on DTBench: 61.2%, #100 of 146, with 68% of the field scoring higher. Claude Opus 5.5 (max) leads at 98.9%; the closest result above is Magistral Small 1.2 at 61.3%. It covers dynamic tool-use benchmark. The board median is 68.8%, so mistral-large-2407 is 7.6 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

mistral-large-2407 lands below the middle on GPQA Diamond: 49.0%, #190 of 275, with 69% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is mistral-small-3.2-2506 at 49.1%. It covers expert-level science questions. The board median is 71.7%, so mistral-large-2407 is 22.7 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

mistral-large-2407 lands below the middle on OTIS Mock AIME: 8.5%, #140 of 189, with 74% of the field scoring higher. Claude Fable 5.1 (max) leads at 100.0%; the closest result above is Claude 3.5 Sonnet (Oct 2024) at 8.5%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so mistral-large-2407 is 49.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

SimpleBench is a weak spot. mistral-large-2407 scores 22.5%, #55 of 61, behind 89% of the models measured. The leader, Claude Fable 5 (max), reaches 81.9%. It covers trick questions that test common sense. The board median is 41.4%, so mistral-large-2407 is 18.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

Reasoning, maths and science: weak, ahead of 22% of the field on average across 3 benchmarks. Its best board here is GPQA Diamond (#190 of 275) and its weakest is SimpleBench (#55 of 61).

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so mistral-large-2407 costs more 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 GPT-4o (May 2024) ($2.50) and GPT-4o (Nov 2024) ($2.50).

Release history

The Mistral AI model released before it was open-mistral-nemo-2407 on 2024-07-18, which scores 45.6. The next one was mistral-small-2409 on 2024-09-17, at 46.3.

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

#677 grok-2-1212 (43.4)
#678 qwen3-8b (43.4)
#679 Llama-3.2-3B (43.4)
#681 granite-3.0-2b-base (43.3)
#682 open-mixtral-8x7b (43.2)
#683 SWE-Llama 7B (43.2)