Alibaba / Qwen, released Sep 2, 2026

Qwen3.8 Max 0902price, context, benchmarks and release details

Provisional: not enough results to rank yet 40% confidence, 2 of 7 expected sources in

51.9

SI Score

Not ranked yet

Input, per 1M tokens: $1.65
Output, per 1M tokens: $4.95
Context window: 1M
Max output: 131K
Released: Sep 2, 2026

How the score breaks down

Coding 27.0

Math 59.9

Preference —

Reasoning 92.3

Weights: reasoning 30%, math 15%, coding 40%, preference 15%. Results use fixed 0–100 scales before averaging, and thin evidence is pulled toward 50. Method si-v3-retained-evidence-2, computed Oct 9, 2026, 06:15 UTC.

Around it on the leaderboard

Full leaderboard

Benchmark results

5 benchmarks, 5 results

Each row shows the best published result. Where a model was tested at several settings, such as reasoning effort, open the row to see each one. Hover or tap a value for its source.

GPQA Diamondreasoning 92.3% 92.3

FrontierMath Tier 4 (v2)math 34.1% 34.1

FrontierMath Tiers 1–3 (v2)math 65.6% 65.6

OTIS Mock AIME 2024–2025math 100% 100.0

Terminal-Bench 4.0coding 27.0% 27.0

Normalization uses a fixed 0–100 scale for each unit, independent of other models. Compare evaluation conditions before reading a small gap as decisive. “Lab-reported” marks the provider's own published figure.

Details and sources

Open weights: No
License: not yet reported
Input modalities: text, image, video, pdf
First seen by SuperIndex: Oct 8, 2026
Coverage: 32% of expected source weight

Reported (2)

Epoch AI BenchmarkingOct 8, 2026
Terminal-BenchOct 8, 2026

Awaiting (5)

ARC Prize13% of weight
Humanity’s Last Exam13% of weight
Official model cards via models.dev4% of weight
LiveBench13% of weight
LMArena / Arena25% of weight

Confidence rises as pending sources publish. Some sources never cover some models, so confidence reaches 100% at 80% of expected weight.