Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Claude 4.5 Haiku (Non-reasoning)
Anthropic
- Gemini 3.1 Flash-Lite
Google
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Claude 4.5 Haiku (Non-reasoning) Anthropic | Gemini 3.1 Flash-Lite | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 15.4 | Best: 15.6 | |
| Coding | Best: 43.9 | 34.7 | |
| Math | 39 | — | |
| Agentic | Best: 8 | 1.6 | |
| Speed | 87.8 t/s | Best: 342 t/s | |
| TTFT | Best: 0.5 s | 4.25 s | |
| Input · $ / 1M tokens | $1×4 relative to the lowest price among the compared models | Best: $0.25 | |
| Output · $ / 1M tokens | $5×3.3 relative to the lowest price among the compared models | Best: $1.50 | |
| Context window | 200K | Best: 1M | |
| Reasoning | No | Yes | |
| Open weights | No | No | |
| Cost / task | — | $0.0602 |
Intelligence
- Claude 4.5 Haiku (Non-reasoning)
- 15.4
- Gemini 3.1 Flash-Lite
- Best: 15.6
Coding
- Claude 4.5 Haiku (Non-reasoning)
- Best: 43.9
- Gemini 3.1 Flash-Lite
- 34.7
Math
- Claude 4.5 Haiku (Non-reasoning)
- 39
- Gemini 3.1 Flash-Lite
- —
Agentic
- Claude 4.5 Haiku (Non-reasoning)
- Best: 8
- Gemini 3.1 Flash-Lite
- 1.6
Speed
- Claude 4.5 Haiku (Non-reasoning)
- 87.8 t/s
- Gemini 3.1 Flash-Lite
- Best: 342 t/s
TTFT
- Claude 4.5 Haiku (Non-reasoning)
- Best: 0.5 s
- Gemini 3.1 Flash-Lite
- 4.25 s
Input · $ / 1M tokens
- Claude 4.5 Haiku (Non-reasoning)
- $1×4 relative to the lowest price among the compared models
- Gemini 3.1 Flash-Lite
- Best: $0.25
Output · $ / 1M tokens
- Claude 4.5 Haiku (Non-reasoning)
- $5×3.3 relative to the lowest price among the compared models
- Gemini 3.1 Flash-Lite
- Best: $1.50
Context window
- Claude 4.5 Haiku (Non-reasoning)
- 200K
- Gemini 3.1 Flash-Lite
- Best: 1M
Reasoning
- Claude 4.5 Haiku (Non-reasoning)
- No
- Gemini 3.1 Flash-Lite
- Yes
Open weights
- Claude 4.5 Haiku (Non-reasoning)
- No
- Gemini 3.1 Flash-Lite
- No
Cost / task
- Claude 4.5 Haiku (Non-reasoning)
- —
- Gemini 3.1 Flash-Lite
- $0.0602
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 4.5 Haiku (Non-reasoning)15.4 · $2
- Gemini 3.1 Flash-Lite15.6 · $0.563