codestral-2508: benchmark scores, price and ranking

codestral-2508 from Mistral AI ranks #486 of 743 LLMs on the LLMs Tiger aggregate benchmark score (46.8), based on 1 benchmark results captured up to 2026-10-13.

Organisation: Mistral AI
Type: Frontier model
Open weights: No
Released: 2025-07-30 (source: epoch)
Cheapest API price: $0.300 in / $0.900 out per million tokens (via mistral, observed 2026-10-13T20:47Z)
Aggregate rank: #486 of 743 (score 46.8)

Across the 1 benchmark where at least ten models are scored, codestral-2508 is in the top 10% on 0 and in the top half on 0.

Its cheapest listed input price, $0.300 per million tokens, is lower than that of 58% of the 427 models with a listed price.

codestral-2508 benchmark results

codestral-2508 benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
ALE-Bench	138	#79 of 79	Epoch AI Benchmarking Hub	2026-10-13

About codestral-2508

codestral-2508 is a frontier model from Mistral AI. It was released on 2025-07-30, according to Epoch AI. The cheapest API listing we track charges $0.300 per million input tokens and $0.900 per million output tokens, through mistral. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.

Where codestral-2508 stands

On our aggregate score, codestral-2508 is #486 of 743 ranked models, in the lower half. Its score is 46.8; the scale is centred on 50, so it sits 3.2 points below the typical model. That beats 35% of the ranked field. Among the 44 ranked Mistral AI models it is #13. The next one up is magistral-small-2506 at 47.0. The next one down is mistral-medium-2312 at 46.7.

codestral-2508, benchmark by benchmark

ALE-Bench is a weak spot. codestral-2508 scores 138, #79 of 79, behind 99% of the models measured. The leader, GPT-6 Astra (max), reaches 2,951. It covers AtCoder heuristic-optimisation contests (performance rating). The board median is 764, so codestral-2508 is 626 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so codestral-2508 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 qwen3.6-plus ($0.325) and Qwen3-Coder-480B-A35B-Instruct ($0.380).

Release history

The Mistral AI model released before it was mistral-small-3.2-2506 on 2025-06-20, which scores 46.4. The next one was mistral-medium-2508 on 2025-08-12, at 43.7.

Reading these numbers

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

Models ranked nearby

#483 Command A+ (46.8)
#484 MiniMax-M2.5 (46.8)
#485 o4-mini (high) (46.8)
#487 Mellum2-12B-A2.5B-Instruct (46.8)
#488 Gemini 2.0 Pro Exp (Feb 2025) (46.7)
#489 mistral-medium-2312 (46.7)