Skip to content
Model Pareto

Devstral Small 2

Mistral AIOpen weightsartificialanalysis.ai ↗
Input
—
Output
—
Speed
~99tok/sest.
Context
256Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Devstral Small 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
1× B200 180GB
BF16 weights
Throughput
~4,962 tok/s
many requests batched
Price
$0.19–1.67 /M tok
busy → light use
On your own machine
RTX 5090 32GB (int4, ~100 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • BF16 weights (24B params) + 25% KV-cache headroom ≈ 60 GB
  • 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~4,962 output tok/s aggregate at batch 142 (bandwidth-bound)
  • Blended 3:1 input:output; prefill ~22,148 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

~#23 of 24 (estimated)~44.6%
  1. #1Claude Fable 5.293.0%
  2. #2Claude Opus 5.589.9%
  3. #22Muse Glimmer51.2%
  4. ~#23Devstral Small 2Estimated44.6%
  5. #23Nex-N2.5-Mini43.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#43 of 46 (estimated)~35.5%
  1. #1Gemini 4 Argon78.8%
  2. #2DeepSeek V4.1 Flash 101777.0%
  3. #42Nex-N2.5-Mini36.1%
  4. ~#43Devstral Small 2Estimated35.5%
  5. #43Hy328.0%
No published score — estimated from related benchmarks
~#25 of 26 (estimated)~27.4
  1. #1Claude Opus 5.561.7
  2. #2Claude Opus 559.7
  3. #24GPT-6 Luna31.1
  4. ~#25Devstral Small 2Estimated27.4
  5. #25Muse Spark Open26.3
No published score — estimated from related benchmarks

Writing & chat

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Devstral Small 2Estimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
~last of 12 (estimated)below measured range (<74.5%)
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #11Gemini 3.5 Flash-Lite74.5%
  4. ~#12Devstral Small 2Estimated<74.5%
No published score — estimated from related benchmarks
~last of 8 (estimated)below measured range (<75.8%)
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #7Muse Glimmer75.8%
  4. ~#8Devstral Small 2Estimated<75.8%
No published score — estimated from related benchmarks
ChartographyEstimated
~last of 25 (estimated)below measured range (<9.0%)
  1. #1Claude Fable 5.273.4%
  2. #2GPT-6 Astra71.0%
  3. #24Mistral Large 39.0%
  4. ~#25Devstral Small 2Estimated<9.0%
No published score — estimated from related benchmarks

Hard reasoning

Agents