Devstral (2512): benchmark scores, price and ranking

Devstral (2512) from mistral ranks #238 of 743 LLMs on the LLMs Tiger aggregate benchmark score (49.7), based on 1 benchmark results captured up to 2026-10-13.

Organisation: mistral
Type: Open-weight / local model
Open weights: Yes
Cheapest API price: $0.400 in / $2.00 out per million tokens (via mistral, observed 2026-10-13T20:47Z)
Aggregate rank: #238 of 743 (score 49.7)

Across the 1 benchmark where at least ten models are scored, Devstral (2512) 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.

Devstral (2512) benchmark results

Devstral (2512) benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
SWE-bench Verified	53.8%	#41 of 73	SWE-bench Verified leaderboard	2026-10-13

About Devstral (2512)

Devstral (2512) is an open-weight model that can run on your own hardware from mistral. The cheapest API listing we track charges $0.400 per million input tokens and $2.00 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 Devstral (2512) stands

On our aggregate score, Devstral (2512) is #238 of 743 ranked models, around the middle of the table. Its score is 49.7; the scale is centred on 50, so it sits 0.3 points below the typical model. That beats 68% of the ranked field. Among the 2 ranked mistral models it is #2. The next one up is Devstral Small (2512) at 49.9.

Devstral (2512), benchmark by benchmark

Devstral (2512) lands below the middle on SWE-bench Verified: 53.8%, #41 of 73, with 55% of the field scoring higher. Claude Opus 4.7 (max) leads at 83.5%; the closest result above is glm-4.5 at 54.2%. It covers real GitHub issues resolved. The board median is 56.4%, so Devstral (2512) is 2.6 points below it. Source: SWE-bench Verified leaderboard, captured 2026-10-13.

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so Devstral (2512) 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), DeepSeek V4 Flash 0731 (max) ($0.016, 53.1). Similar scores cost more on mimo-v2.5-pro ($0.435) and Kimi K2.5 ($0.450).

Reading these numbers

The 1 score on this page comes from 1 source: SWE-bench Verified leaderboard (1). 1 of them come from an official leaderboard and 0 from datasets or third-party runs. With 1 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#235 claude-haiku-4-5-20251001_1K (49.8)
#236 Qwen2.5-32B (49.7)
#237 QwQ-32B (49.7)
#239 claude-opus-4-1-20250805 (49.7)
#240 Kimi K2 Thinking (Together) (49.7)
#241 Frogboss 32B 2510 (49.7)