Qwen3.8 Max 0902: Price, Context, Benchmarks, and Release Details
51.9
SI Score (method si-v3-retained-evidence-2)
40% confidence 40 percent, Low confidence — 2 of 7 expected sources in
Coverage 32% of expected source weight · 100% confidence at 80% coverage
Pillar breakdown
Coding (weight 40 percent) 27.0
Math (weight 15 percent) 59.9
Preference (weight 15 percent) —
Reasoning (weight 30 percent) 92.3
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
- $1.65Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤1M; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - Output price / 1M
- $4.95Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤1M; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - 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
- Sep 2, 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, video, pdfmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗
Benchmark results
5 results| Benchmark | Raw result | Normalized (0–100) | Pillar |
|---|---|---|---|
| frontiermath tier 4 v2 | 34.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Sep 2, 2026
Retrieved Oct 9, 2026 · CC-BY Open source ↗ | 34.1 | math |
| frontiermath tiers 1 3 v2 | 65.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Sep 2, 2026
Retrieved Oct 9, 2026 · CC-BY Open source ↗ | 65.6 | math |
| gpqa diamond | 92.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Sep 2, 2026
Retrieved Oct 9, 2026 · CC-BY Open source ↗ | 92.3 | reasoning |
| otis mock aime 2024 2025 | 100%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Sep 2, 2026
Retrieved Oct 9, 2026 · CC-BY Open source ↗ | 100.0 | math |
| terminal bench v4 0 | 27.0%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; maxPublished Oct 6, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation Open source ↗ | 27.0 | 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 (2)
- Epoch AI Benchmarking · arrived Oct 8, 2026
- Terminal-Bench · arrived Oct 8, 2026
pending Awaiting (5)
- ARC Prize · carries 13% of expected weight
- Humanity’s Last Exam · carries 13% of expected weight
- Official model cards via models.dev · carries 4% of expected weight
- LiveBench · carries 13% of expected weight
- LMArena / Arena · carries 25% 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.