Skip to content
Model Pareto

Devstral 2

Mistral AIOpen weightsartificialanalysis.ai ↗
Compare with nearest rivalsCompare with…
Input
—
Output
—
Speed
~84tok/sest.
Context
256Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Devstral 2. Price = AA median host price.

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs. No API sells this model, so this is its price on the chart.

Hardware
4× H100 80GB
FP8 weights
Throughput
~3,028 tok/s
many requests batched
Price
$0.53–5.07 /M tok
busy → light use
On your own machine
Mac Studio M5 Max 128GB (int4, ~7 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (125B params) + 25% KV-cache headroom ≈ 156 GB
  • 4× H100 80GB at $2.69–$6.88/GPU-hour on-demand (2026-09-24)
  • ~3,028 output tok/s aggregate at batch 88 (bandwidth-bound)
  • Blended 3:1 input:output; prefill ~14,961 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

SWE-bench Pro (Public)Estimated
~#18 of 19 (estimated)~46.1%
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #17Muse Glimmer51.2%
  4. ~#18Devstral 2Estimated46.1%
  5. #18Nex-N2.5-Mini43.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#29 of 31 (estimated)~41.3%
  1. #1DeepSeek V4.1 Flash74.2%
  2. #2Grok 4.772.6%
  3. #28Qwen3.8 27B42.2%
  4. ~#29Devstral 2Estimated41.3%
  5. #29Nex-N2.5-Mini36.1%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~last of 15 (estimated)below measured range (<41.1)
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #14GPT-6 Luna41.1
  4. ~#15Devstral 2Estimated<41.1
No published score — estimated from related benchmarks

Writing & chat

MMMLUEstimated
~last of 5 (estimated)below measured range (<81.3%)
  1. #1Gemini 3.1 Pro92.6%
  2. #2Gemma 4 31B88.4%
  3. #4gpt-oss-120b81.3%
  4. ~#5Devstral 2Estimated<81.3%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#45 of 54 (estimated)~1321 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #44INTELLECT-3Few votes1327
  4. ~#45Devstral 2Estimated1321
  5. #45Llama 4 Maverick1311
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#46 of 54 (estimated)~1345 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #45Llama 3.1 Nemotron Ultra 253B v1Few votes1348
  4. ~#46Devstral 2Estimated1345
  5. #46Olmo 3.1 32B Instruct1330
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#24 of 26 (estimated)~1329 Elo
  1. #1GPT-6 Astra2173
  2. #2Claude Fable 5.12162
  3. #23Gemma 4 31B1368
  4. ~#24Devstral 2Estimated1329
  5. #24gpt-oss-120b961
No published score — estimated from related benchmarks

Hard reasoning

Agents

OSWorld-VerifiedEstimated
~#11 of 12 (estimated)~61.1%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #10Muse Glimmer65.9%
  4. ~#11Devstral 2Estimated61.1%
  5. #11Claude Haiku 4.550.7%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. #4GPT-5.547.5%
  4. ~#5Devstral 2Estimated<47.5%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#15 of 18 (estimated)~50.2%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #14Inkling77.1%
  4. ~#15Devstral 2Estimated50.2%
  5. #15Mistral Medium 3.548.6%
No published score — estimated from related benchmarks