Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Claude Opus 4.5 (Reasoning)
Anthropic
- MiniMax-M3
MiniMax
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Claude Opus 4.5 (Reasoning) Anthropic | MiniMax-M3 MiniMax | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 29.1 | Best: 29.2 | |
| Coding | — | 58.6 | |
| Math | 91.3 | — | |
| Agentic | — | 29.5 | |
| Cyber Index | — | 22.4% | |
| Speed | 48.5 t/s | Best: 99.6 t/s | |
| TTFT | 18.1 s | Best: 1.43 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 | 200K | Best: 1M | |
| Reasoning | Yes | Yes | |
| Open weights | No | Yes | |
| Cost / task | — | $0.508 |
Intelligence
- Claude Opus 4.5 (Reasoning)
- 29.1
- MiniMax-M3
- Best: 29.2
Coding
- Claude Opus 4.5 (Reasoning)
- —
- MiniMax-M3
- 58.6
Math
- Claude Opus 4.5 (Reasoning)
- 91.3
- MiniMax-M3
- —
Agentic
- Claude Opus 4.5 (Reasoning)
- —
- MiniMax-M3
- 29.5
Cyber Index
- Claude Opus 4.5 (Reasoning)
- —
- MiniMax-M3
- 22.4%
Speed
- Claude Opus 4.5 (Reasoning)
- 48.5 t/s
- MiniMax-M3
- Best: 99.6 t/s
TTFT
- Claude Opus 4.5 (Reasoning)
- 18.1 s
- MiniMax-M3
- Best: 1.43 s
Input · $ / 1M tokens
- Claude Opus 4.5 (Reasoning)
- $5×16.7 relative to the lowest price among the compared models
- MiniMax-M3
- Best: $0.30
Output · $ / 1M tokens
- Claude Opus 4.5 (Reasoning)
- $25×20.8 relative to the lowest price among the compared models
- MiniMax-M3
- Best: $1.20
Context window
- Claude Opus 4.5 (Reasoning)
- 200K
- MiniMax-M3
- Best: 1M
Reasoning
- Claude Opus 4.5 (Reasoning)
- Yes
- MiniMax-M3
- Yes
Open weights
- Claude Opus 4.5 (Reasoning)
- No
- MiniMax-M3
- Yes
Cost / task
- Claude Opus 4.5 (Reasoning)
- —
- MiniMax-M3
- $0.508
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 4.5 (Reasoning)29.1 · $10
- MiniMax-M329.2 · $0.525