Skip to content
Model Pareto

Mistral Large 3

Mistral AIOpen weightsmistral.ai ↗
Compare with nearest rivalsCompare with…
Input
$0.50/M tok
Output
$1.50/M tok
Blended
$0.75/M tok · 3:1
Speed
77tok/s
Context
256Ktokens

Previous-generation open-weights flagship. Main release is FP8 (card: "FP8 on a single node of B200s or H200s"; BF16 provided "if needed").

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.

Hardware
8× B200 180GB
FP8 weights
Throughput
~20,662 tok/s
many requests batched
Price
$0.28–2.49 /M tok
busy → light use
On your own machine
Mac Studio M5 Ultra 512GB (int4, ~41 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (675B params, 41B active per token) + 25% KV-cache headroom ≈ 844 GB
  • 8× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~20,662 output tok/s aggregate at batch 591 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~207,439 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)~47.5%
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #17Muse Glimmer51.2%
  4. ~#18Mistral Large 3Estimated47.5%
  5. #18Nex-N2.5-Mini43.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#28 of 31 (estimated)~43.9%
  1. #1DeepSeek V4.1 Flash74.2%
  2. #2Grok 4.772.6%
  3. #27Qwen3.8 Max (0902)51.0%
  4. ~#28Mistral Large 3Estimated43.9%
  5. #28Qwen3.8 27B42.2%
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. ~#15Mistral Large 3Estimated<41.1
No published score — estimated from related benchmarks

Writing & chat

MMMLUEstimated
~#4 of 5 (estimated)~81.5%
  1. #1Gemini 3.1 Pro92.6%
  2. #2Gemma 4 31B88.4%
  3. #3Claude Haiku 4.583.0%
  4. ~#4Mistral Large 3Estimated81.5%
  5. #4gpt-oss-120b81.3%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Verified
#36 of 531397 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #35Nemotron 3 Ultra1405
  4. #36Mistral Large 31397
  5. #36Qwen3.5 122B A10B1397
lmarena.ai · 2026-09-24
LMArena Text (Elo)Verified
#38 of 531413 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #37Claude Haiku 4.51415
  4. #38Mistral Large 31413
  5. #39GPT-5.4 nano1402
lmarena.ai · 2026-09-24

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Mistral Large 3Estimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~last of 9 (estimated)below measured range (<74.5%)
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #8Gemini 3.5 Flash-Lite74.5%
  4. ~#9Mistral Large 3Estimated<74.5%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~last of 8 (estimated)below measured range (<75.8%)
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #7Muse Glimmer75.8%
  4. ~#8Mistral Large 3Estimated<75.8%
No published score — estimated from related benchmarks

Hard reasoning

Agents

OSWorld-VerifiedEstimated
~#11 of 12 (estimated)~60.6%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #10Muse Glimmer65.9%
  4. ~#11Mistral Large 3Estimated60.6%
  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. ~#5Mistral Large 3Estimated<47.5%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#15 of 18 (estimated)~49.1%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #14Inkling77.1%
  4. ~#15Mistral Large 3Estimated49.1%
  5. #15Mistral Medium 3.548.6%
No published score — estimated from related benchmarks