Model Comparator
Compare up to four models using the same criteria.
2 models compared
- GPT-5 mini (High)
OpenAI
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | GPT-5 mini (High) OpenAI | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | Best: 16.8 | 16.7 | |
| Coding | 15.6 | Best: 39.3 | |
| Math | 90.7 | — | |
| Agentic | Best: 6.8 | 2.9 | |
| Speed | Best: 146 t/s | 65.7 t/s | |
| TTFT | 47.4 s | Best: 0.97 s | |
| Input · $ / 1M tokens | $0.25×2.5 relative to the lowest price among the compared models | Best: $0.10 | |
| Output · $ / 1M tokens | $2×5 relative to the lowest price among the compared models | Best: $0.40 | |
| Context window | Best: 400K | 256K | |
| Reasoning | Yes | Yes | |
| Open weights | No | Yes | |
| Cost / task | $0.0535 | — |
Intelligence
- GPT-5 mini (High)
- Best: 16.8
- Gemma 4 26B A4B (Reasoning)
- 16.7
Coding
- GPT-5 mini (High)
- 15.6
- Gemma 4 26B A4B (Reasoning)
- Best: 39.3
Math
- GPT-5 mini (High)
- 90.7
- Gemma 4 26B A4B (Reasoning)
- —
Agentic
- GPT-5 mini (High)
- Best: 6.8
- Gemma 4 26B A4B (Reasoning)
- 2.9
Speed
- GPT-5 mini (High)
- Best: 146 t/s
- Gemma 4 26B A4B (Reasoning)
- 65.7 t/s
TTFT
- GPT-5 mini (High)
- 47.4 s
- Gemma 4 26B A4B (Reasoning)
- Best: 0.97 s
Input · $ / 1M tokens
- GPT-5 mini (High)
- $0.25×2.5 relative to the lowest price among the compared models
- Gemma 4 26B A4B (Reasoning)
- Best: $0.10
Output · $ / 1M tokens
- GPT-5 mini (High)
- $2×5 relative to the lowest price among the compared models
- Gemma 4 26B A4B (Reasoning)
- Best: $0.40
Context window
- GPT-5 mini (High)
- Best: 400K
- Gemma 4 26B A4B (Reasoning)
- 256K
Reasoning
- GPT-5 mini (High)
- Yes
- Gemma 4 26B A4B (Reasoning)
- Yes
Open weights
- GPT-5 mini (High)
- No
- Gemma 4 26B A4B (Reasoning)
- Yes
Cost / task
- GPT-5 mini (High)
- $0.0535
- Gemma 4 26B A4B (Reasoning)
- —
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.
- GPT-5 mini (High)16.8 · $0.688
- Gemma 4 26B A4B (Reasoning)16.7 · $0.175