Skip to content
Model Pareto

MiniMax-M3.1-Flash

MiniMaxOpen weightshuggingface.co ↗
Compare with nearest rivalsCompare with…
Input
$0.15/M tok
Output
$0.60/M tok
Blended
$0.262/M tok · 3:1
Speed
87tok/s
Context
1Mtokens

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× H200 141GB
FP8 weights
Throughput
~20,773 tok/s
many requests batched
Price
$0.18–1.46 /M tok
busy → light use
On your own machine
Mac Studio M5 Ultra 512GB (int4, ~73 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (428B params, 23B active per token) + 40% KV-cache headroom ≈ 599 GB
  • 8× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
  • ~20,773 output tok/s aggregate at batch 747 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~162,622 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 VerifiedEstimated
~#2 of 20 (estimated)~85.9%
  1. #1Claude Opus 596.0%
  2. ~#2MiniMax-M3.1-FlashEstimated85.9%
  3. #2Claude Sonnet 585.2%
No published score — estimated from related benchmarks

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2MiniMax-M3.1-FlashEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~88.4%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #2Qwen3.8 27B91.1%
  4. ~#4MiniMax-M3.1-FlashEstimated88.4%
  5. #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#19 of 47 (estimated)~18.0%
  1. #1Muse Wonder Full32.6%
  2. #2GPT-6 Astra31.0%
  3. #18MiMo-V2.6-Pro19.2%
  4. ~#19MiniMax-M3.1-FlashEstimated18.0%
  5. #19Gemini 3.1 Pro17.8%
No published score — estimated from related benchmarks
ChartographyEstimated
~#9 of 24 (estimated)~29.3%
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #8GPT-5.531.0%
  4. ~#9MiniMax-M3.1-FlashEstimated29.3%
  5. #9GPT-6 Luna29.1%
No published score — estimated from related benchmarks

Hard reasoning

GPQA DiamondEstimated
~#2 of 191 (estimated)~95.4%
  1. #1GPT-6 Astra96.1%
  2. ~#2MiniMax-M3.1-FlashEstimated95.4%
  3. #2Gemini 3.8 Flash95.3%
No published score — estimated from related benchmarks
AIME (latest)Estimated
~#2 of 33 (estimated)~98.9%
  1. #1GLM-5.3 NVFP499.5%
  2. ~#2MiniMax-M3.1-FlashEstimated98.9%
  3. #2Beam 1.0 501B A23B97.7%
No published score — estimated from related benchmarks

AgentsEstimated from other categories

τ²-bench (Telecom)Estimated
~#3 of 120 (estimated)~98.0%
  1. #1Step 3.7 Flash98.5%
  2. #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
  3. ~#3MiniMax-M3.1-FlashEstimated98.0%
  4. #3Gemini 3.1 Pro95.6%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#8 of 15 (estimated)~79.7%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #7Muse Spark Open80.4%
  4. ~#8MiniMax-M3.1-FlashEstimated79.7%
  5. #8GPT-5.578.7%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3MiniMax-M3.1-FlashEstimated53.8%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#8 of 22 (estimated)~86.5%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #7GPT-5.6 Terra87.5%
  4. ~#8MiniMax-M3.1-FlashEstimated86.5%
  5. #8Gemini 3.1 Pro85.9%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#18 of 91 (estimated)~1581 Elo
  1. #1Claude Opus 5.51866
  2. #2Muse Wonder Full1857
  3. #17Step 5 Preview1584
  4. ~#18MiniMax-M3.1-FlashEstimated1581
  5. #18GPT-6 Astra1574
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#25 of 84 (estimated)~52.0%
  1. #1Muse Wonder Full71.3%
  2. #2Claude Opus 5.569.5%
  3. #24GPT-6 Luna53.2%
  4. ~#25MiniMax-M3.1-FlashEstimated52.0%
  5. #25Step 5 Preview51.0%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#17 of 91 (estimated)~37.6%
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #16GPT-5.539.0%
  4. ~#17MiniMax-M3.1-FlashEstimated37.6%
  5. #17Claude Sonnet 537.3%
No published score — estimated from related benchmarks
Not comparable across labs (1)

Kept for reference, not counted in rankings: these use a lab-specific task set, answer key or scoring, so scores can't be compared fairly across labs. Only published scores are shown.