Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Claude Opus 5 (Medium)
Anthropic
- DeepSeek V4.1 Flash 1017 (Max)
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Claude Opus 5 (Medium) Anthropic | DeepSeek V4.1 Flash 1017 (Max) DeepSeek | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 44.8 | Best: 45.1 | |
| Coding | 74.3 | — | |
| Agentic | 46.2 | — | |
| Speed | 55.5 t/s | Best: 204 t/s | |
| TTFT | 3.88 s | Best: 1.06 s | |
| Input · $ / 1M tokens | $5×16.7 relative to the lowest price among the compared models | Best: $0.30 | |
| Output · $ / 1M tokens | $25×20.8 relative to the lowest price among the compared models | Best: $1.20 | |
| Context window | 1M | 1M | |
| Reasoning | Yes | Yes | |
| Open weights | No | Yes | |
| Cost / task | $2.19×8.4 relative to the lowest price among the compared models | Best: $0.262 |
Intelligence
- Claude Opus 5 (Medium)
- 44.8
- DeepSeek V4.1 Flash 1017 (Max)
- Best: 45.1
Coding
- Claude Opus 5 (Medium)
- 74.3
- DeepSeek V4.1 Flash 1017 (Max)
- —
Agentic
- Claude Opus 5 (Medium)
- 46.2
- DeepSeek V4.1 Flash 1017 (Max)
- —
Speed
- Claude Opus 5 (Medium)
- 55.5 t/s
- DeepSeek V4.1 Flash 1017 (Max)
- Best: 204 t/s
TTFT
- Claude Opus 5 (Medium)
- 3.88 s
- DeepSeek V4.1 Flash 1017 (Max)
- Best: 1.06 s
Input · $ / 1M tokens
- Claude Opus 5 (Medium)
- $5×16.7 relative to the lowest price among the compared models
- DeepSeek V4.1 Flash 1017 (Max)
- Best: $0.30
Output · $ / 1M tokens
- Claude Opus 5 (Medium)
- $25×20.8 relative to the lowest price among the compared models
- DeepSeek V4.1 Flash 1017 (Max)
- Best: $1.20
Context window
- Claude Opus 5 (Medium)
- 1M
- DeepSeek V4.1 Flash 1017 (Max)
- 1M
Reasoning
- Claude Opus 5 (Medium)
- Yes
- DeepSeek V4.1 Flash 1017 (Max)
- Yes
Open weights
- Claude Opus 5 (Medium)
- No
- DeepSeek V4.1 Flash 1017 (Max)
- Yes
Cost / task
- Claude Opus 5 (Medium)
- $2.19×8.4 relative to the lowest price among the compared models
- DeepSeek V4.1 Flash 1017 (Max)
- Best: $0.262
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
- DeepSeek V4.1 Flash 1017 (Max)45.1 · $0.262