Qwen3-Max-Instruct
ModelActiveby Alibaba (Qwen) · family “qwen3-max-instruct”
Epoch Capabilities Index
Not scored by Epoch AI
Released
24 Sep 2025
Context window
Unknown
Max output
Unknown
Input $ / 1M tokens
Unknown
Output $ / 1M tokens
Unknown
Cached input $ / 1M
Unknown
Each benchmark shown separately with its own source
Benchmark results (11)
| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| LMCA | agents | 28.3% | 43% | — | — | External ↗ |
| DTBench | reasoning | 82.1% | 83% | — | — | External ↗ |
| Mystery Game Puzzles | games | 5.0% ±2.2 | 6% | — | 27 Aug 2026 | Epoch ↗ |
| FrontierMath-Tiers-1-3-v2-Private | math | 18.9% ±2.3 | 20% | — | 30 Aug 2026 | Eval log ↗ |
| CL-bench | long-context | 14.5% | 52% | — | — | External ↗ |
| Chess Puzzles | games | 4.0% ±2.0 | 6% | — | 10 Dec 2025 | Eval log ↗ |
| SimpleQA Verified | knowledge | 48.7% ±1.6 | 64% | — | 27 Aug 2026 | Eval log ↗ |
| Fiction.LiveBench | long-context | 66.7% | 69% | — | — | External ↗ |
| OTIS Mock AIME 2024-2025 | math | 73.3% ±5.9 | 73% | — | 6 Oct 2025 | Eval log ↗ |
| GPQA diamond | science | 72.6% ±2.7 | 76% | — | 6 Oct 2025 | Eval log ↗ |
| MATH level 5 | math | 97.1% ±0.4 | 99% | — | 9 Oct 2025 | Epoch ↗ |
Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.
API list price over time
Price history
$ per 1M tokens
No data recorded for this period
0 observations (OpenRouter listing). History accumulates with every ingest run; a single point means no change has been observed yet.
Events
- Benchmark30d agoEpoch AI evaluates Qwen3-Max-InstructEpoch AI Benchmarking Hub
- Benchmark33d agoEpoch AI evaluates Qwen3-Max-InstructEpoch AI Benchmarking Hub
- Model launch12mo agoAlibaba releases Qwen3-Max-InstructEpoch AI Benchmarking Hub