Skip to content
Model Pareto

Qwen3.8 2.4T A95B

Alibaba QwenOpen weightshuggingface.co ↗
Compare with nearest rivalsCompare with…
Input
$2.00/M tok
Output
$6.00/M tok
Blended
$3.00/M tok · 3:1
Speed
38tok/s
Context
262Ktokens

Open-weights checkpoint behind Qwen3.8 Max; priced at Qwen3.8 Max API rates.

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
24× B200 180GB
FP8 weights
Throughput
~27,655 tok/s
many requests batched
Price
$0.66–5.85 /M tok
busy → light use
On your own machine
Too large
needs data-center GPUs
Assumptions (5)
  • FP8 weights (2400B params, 95B active per token) + 25% KV-cache headroom ≈ 3000 GB
  • 24× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~27,655 output tok/s aggregate at batch 931 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~228,292 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
~#3 of 14 (estimated)~82.4%
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. ~#3Qwen3.8 2.4T A95BEstimated82.4%
  4. #3Gemini 3.1 Pro80.6%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#4 of 20 (estimated)~89.4%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. #3Qwen3.8 27B90.3%
  4. ~#4Qwen3.8 2.4T A95BEstimated89.4%
  5. #4Nemotron 3 Ultra89.0%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~#11 of 15 (estimated)~46.8
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #10Grok 4.647.0
  4. ~#11Qwen3.8 2.4T A95BEstimated46.8
  5. #11Qwen3.8 Max (0902)43.3
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.

Writing & chat

MMMLUEstimated
~#2 of 5 (estimated)~91.3%
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2Qwen3.8 2.4T A95BEstimated91.3%
  3. #2Gemma 4 31B88.4%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#16 of 54 (estimated)~1449 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #15GPT-5.6 Terra1456
  4. ~#16Qwen3.8 2.4T A95BEstimated1449
  5. #16DeepSeek V4 Pro (0813)1448
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#18 of 54 (estimated)~1460 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #17Claude Sonnet 51461
  4. ~#18Qwen3.8 2.4T A95BEstimated1460
  5. #18GPT-6 Sol1457
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#2 of 25 (estimated)~96.7%
  1. #1Inkling97.1%
  2. ~#2Qwen3.8 2.4T A95BEstimated96.7%
  3. #2Muse Glimmer94.7%
No published score — estimated from related benchmarks

Agents

τ²-bench (Telecom)Estimated
~#2 of 116 (estimated)~98.3%
  1. #1Step 3.7 Flash98.5%
  2. ~#2Qwen3.8 2.4T A95BEstimated98.3%
  3. #2Gemini 3.1 Pro95.6%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#3 of 12 (estimated)~83.1%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. ~#3Qwen3.8 2.4T A95BEstimated83.1%
  4. #3Nex-N2.5-Pro82.2%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~57.3%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Qwen3.8 2.4T A95BEstimated57.3%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#5 of 18 (estimated)~89.9%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #4Claude Opus 590.8%
  4. ~#5Qwen3.8 2.4T A95BEstimated89.9%
  5. #5Nex-N2.5-Pro89.7%
No published score — estimated from related benchmarks