Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Claude Opus 5 (Medium)
Anthropic
- Qwen3.8 Max (0902)
Alibaba
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Claude Opus 5 (Medium) Anthropic | Qwen3.8 Max (0902) Alibaba | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 44.8 | Best: 45.4 | |
| Coding | 74.3 | Best: 76.2 | |
| Agentic | 46.2 | Best: 56 | |
| Speed | Best: 55.5 t/s | 41.7 t/s | |
| TTFT | 3.88 s | Best: 3.07 s | |
| Input · $ / 1M tokens | $5×2.5 relative to the lowest price among the compared models | Best: $2 | |
| Output · $ / 1M tokens | $25×4.2 relative to the lowest price among the compared models | Best: $6 | |
| Context window | Best: 1M | 984K | |
| Reasoning | Yes | Yes | |
| Open weights | No | No | |
| Cost / task | Best: $2.19 | $5.41×2.5 relative to the lowest price among the compared models |
Intelligence
- Claude Opus 5 (Medium)
- 44.8
- Qwen3.8 Max (0902)
- Best: 45.4
Coding
- Claude Opus 5 (Medium)
- 74.3
- Qwen3.8 Max (0902)
- Best: 76.2
Agentic
- Claude Opus 5 (Medium)
- 46.2
- Qwen3.8 Max (0902)
- Best: 56
Speed
- Claude Opus 5 (Medium)
- Best: 55.5 t/s
- Qwen3.8 Max (0902)
- 41.7 t/s
TTFT
- Claude Opus 5 (Medium)
- 3.88 s
- Qwen3.8 Max (0902)
- Best: 3.07 s
Input · $ / 1M tokens
- Claude Opus 5 (Medium)
- $5×2.5 relative to the lowest price among the compared models
- Qwen3.8 Max (0902)
- Best: $2
Output · $ / 1M tokens
- Claude Opus 5 (Medium)
- $25×4.2 relative to the lowest price among the compared models
- Qwen3.8 Max (0902)
- Best: $6
Context window
- Claude Opus 5 (Medium)
- Best: 1M
- Qwen3.8 Max (0902)
- 984K
Reasoning
- Claude Opus 5 (Medium)
- Yes
- Qwen3.8 Max (0902)
- Yes
Open weights
- Claude Opus 5 (Medium)
- No
- Qwen3.8 Max (0902)
- No
Cost / task
- Claude Opus 5 (Medium)
- Best: $2.19
- Qwen3.8 Max (0902)
- $5.41×2.5 relative to the lowest price among the compared models
Each reasoning level remains a separate configuration.
Score and cost
Each line joins the reasoning levels of a compared model; the large point marks the configuration in the table. The top-right corner holds the best score for the lowest cost. Select another point to compare that level.
- Claude Opus 5 (Medium)44.8 · $2.19
- Qwen3.8 Max (0902)45.4 · $5.41