SI Index Data as of Oct 9, 2026

Qwen3.8 Max Preview: Price, Context, Benchmarks, and Release Details

Alibaba / Qwen provisional listing · first seen Oct 8, 2026 · score computed Oct 9, 2026, 01:09 UTC
50.9
SI Score (method si-v3-retained-evidence-2)
6% confidence 6 percent, Low confidence — 1 of 7 expected sources in
Coverage 4% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 77.1
Math (weight 15 percent) —
Preference (weight 15 percent) —
Reasoning (weight 30 percent) 58.4

Pillar weights: reasoning 30% · math 15% · coding 40% · preference 15%. Benchmark results use fixed 0–100 scales before averaging; incomplete evidence is shrunk toward 50.

Facts

Input price / 1M
not yet reported
Output price / 1M
not yet reported
Context window
1Mmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Max output
131Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
Jul 19, 2026models.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Open weights
Nomodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
License
not yet reported
Input modalities
text, image, videomodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗

Benchmark results

5 results
Benchmark Raw result Normalized (0–100) Pillar
gpqa diamond 92.6%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] xhighPublished Aug 3, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		92.6 reasoning
hle 43.6%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] xhigh, no toolsPublished Aug 3, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		43.6 reasoning
hle tools 56.2%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] xhigh, with toolsPublished Aug 3, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		56.2 reasoning
swe bench pro 67.7%Official model cards via models.devLab-reported; metric resolve rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] xhigh; Claude CodePublished Aug 3, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		67.7 coding
terminal bench v2 1 86.6%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] xhigh; 2.1Published Aug 3, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		86.6 coding

Normalization uses fixed absolute 0–100 scales for each unit, independently of other models that have a result on each benchmark. Coverage and evidence breadth still affect the composite; compare the evaluation conditions before reading a small score gap as decisive. “lab-reported” marks the provider's own published figure.

Sources: in and pending

in Reported (1)

  • Official model cards via models.dev · arrived Oct 8, 2026

pending Awaiting (6)

  • ARC Prize · carries 13% of expected weight
  • Epoch AI Benchmarking · carries 25% of expected weight
  • Humanity’s Last Exam · carries 13% of expected weight
  • LiveBench · carries 13% of expected weight
  • LMArena / Arena · carries 25% of expected weight
  • Terminal-Bench · carries 6% of expected weight

The confidence % rises as pending sources publish. Some sources never cover some models — that is why 100% confidence arrives at 80% of expected weight, not at full coverage.