Skip to content
Model Pareto

Qwen3.8 27B

Alibaba QwenOpen weightshuggingface.co ↗
Compare with nearest rivalsCompare with…
Input
$0.50/M tok
Output
$3.00/M tok
Blended
$1.125/M tok · 3:1
Speed
43tok/s
Context
262Ktokens

Open weights.

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
1× B200 180GB
BF16 weights
Throughput
~4,301 tok/s
many requests batched
Price
$0.22–1.93 /M tok
busy → light use
On your own machine
RTX 5090 32GB (int4, ~90 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • BF16 weights (27.8B params) + 25% KV-cache headroom ≈ 70 GB
  • 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~4,301 output tok/s aggregate at batch 123 (bandwidth-bound)
  • Blended 3:1 input:output; prefill ~19,121 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
~#6 of 14 (estimated)~77.8%
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. #5Hy378.0%
  4. ~#6Qwen3.8 27BEstimated77.8%
  5. #6Inkling77.6%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#14 of 19 (estimated)~57.7%
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #13Hy357.9%
  4. ~#14Qwen3.8 27BEstimated57.7%
  5. #14Inkling54.3%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~#14 of 15 (estimated)~41.2
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #13Gemini 3.8 Flash41.9
  4. ~#14Qwen3.8 27BEstimated41.2
  5. #14GPT-6 Luna41.1
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)~89.5%
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2Qwen3.8 27BEstimated89.5%
  3. #2Gemma 4 31B88.4%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Verified
#29 of 531429 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #28Inkling1430
  4. #29Qwen3.8 27B1429
  5. #30MiniMax-M31427
lmarena.ai · 2026-09-24
LMArena Text (Elo)Verified
#31 of 531437 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #30Gemma 4 26B A4B1438
  4. #31Qwen3.8 27B1437
  5. #32MiMo-V2.51434
lmarena.ai · 2026-09-24

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Qwen3.8 27BEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~#5 of 9 (estimated)~80.4%
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #4Qwen3.8-Omni-Flash83.5%
  4. ~#5Qwen3.8 27BEstimated80.4%
  5. #5Muse Glimmer78.8%
No published score — estimated from related benchmarks
ChartographyEstimated
~#14 of 23 (estimated)~24.1%
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #13Gemini 3.1 Pro26.1%
  4. ~#14Qwen3.8 27BEstimated24.1%
  5. #14Grok 4.620.5%
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.

Hard reasoning

AIME (latest)Estimated
~#2 of 25 (estimated)~96.7%
  1. #1Inkling97.1%
  2. ~#2Qwen3.8 27BEstimated96.7%
  3. #2Muse Glimmer94.7%
No published score — estimated from related benchmarks

Agents

τ²-bench (Telecom)Estimated
~#8 of 116 (estimated)~93.3%
  1. #1Step 3.7 Flash98.5%
  2. #2Gemini 3.1 Pro95.6%
  3. #7Qwen3.5 122B A10B93.6%
  4. ~#8Qwen3.8 27BEstimated93.3%
  5. #8Qwen3.7 Plus93.0%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.6%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Qwen3.8 27BEstimated53.6%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#9 of 18 (estimated)~84.9%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #8Gemini 3.1 Pro85.9%
  4. ~#9Qwen3.8 27BEstimated84.9%
  5. #9Claude Sonnet 584.7%
No published score — estimated from related benchmarks