Model Comparator
Compare up to four models using the same criteria.
2 models compared
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Add a model · 2/4 | ||
|---|---|---|---|
| Intelligence | 9.8 | Best: 9.9 | |
| Coding | 12.1 | — | |
| Math | 56.3 | Best: 60.3 | |
| Agentic | 0.9 | — | |
| Speed | 135 t/s | Best: 203 t/s | |
| TTFT | 2.46 s | Best: 0.49 s | |
| Input · $ / 1M tokens | $0.36×1.2 relative to the lowest price among the compared models | Best: $0.30 | |
| Output · $ / 1M tokens | Best: $1.30 | $2.50×1.9 relative to the lowest price among the compared models | |
| Context window | 262K | Best: 1M | |
| Reasoning | Yes | No | |
| Open weights | Yes | No | |
| Cost / task | $0.0659 | — |
Intelligence
- Qwen3 30B A3B 2507 (Reasoning)
- 9.8
- Gemini 2.5 Flash (Non-reasoning)
- Best: 9.9
Coding
- Qwen3 30B A3B 2507 (Reasoning)
- 12.1
- Gemini 2.5 Flash (Non-reasoning)
- —
Math
- Qwen3 30B A3B 2507 (Reasoning)
- 56.3
- Gemini 2.5 Flash (Non-reasoning)
- Best: 60.3
Agentic
- Qwen3 30B A3B 2507 (Reasoning)
- 0.9
- Gemini 2.5 Flash (Non-reasoning)
- —
Speed
- Qwen3 30B A3B 2507 (Reasoning)
- 135 t/s
- Gemini 2.5 Flash (Non-reasoning)
- Best: 203 t/s
TTFT
- Qwen3 30B A3B 2507 (Reasoning)
- 2.46 s
- Gemini 2.5 Flash (Non-reasoning)
- Best: 0.49 s
Input · $ / 1M tokens
- Qwen3 30B A3B 2507 (Reasoning)
- $0.36×1.2 relative to the lowest price among the compared models
- Gemini 2.5 Flash (Non-reasoning)
- Best: $0.30
Output · $ / 1M tokens
- Qwen3 30B A3B 2507 (Reasoning)
- Best: $1.30
- Gemini 2.5 Flash (Non-reasoning)
- $2.50×1.9 relative to the lowest price among the compared models
Context window
- Qwen3 30B A3B 2507 (Reasoning)
- 262K
- Gemini 2.5 Flash (Non-reasoning)
- Best: 1M
Reasoning
- Qwen3 30B A3B 2507 (Reasoning)
- Yes
- Gemini 2.5 Flash (Non-reasoning)
- No
Open weights
- Qwen3 30B A3B 2507 (Reasoning)
- Yes
- Gemini 2.5 Flash (Non-reasoning)
- No
Cost / task
- Qwen3 30B A3B 2507 (Reasoning)
- $0.0659
- Gemini 2.5 Flash (Non-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.
- Qwen3 30B A3B 2507 (Reasoning)9.8 · $0.595
- Gemini 2.5 Flash (Non-reasoning)9.9 · $0.85