token.app › Compare › Claude Haiku 4.5 vs Gemma 4 31B
Claude Haiku 4.5 vs Gemma 4 31B
Gemma 4 31B leads on 3 of 3 shared benchmarks. Gemma 4 31B is 12× cheaper per token on a blended 3:1 basis. Gemma 4 31B accepts the larger context window (262K).
Head to head
Blended price uses a 3:1 input:output mix
| Claude Haiku 4.5 | Gemma 4 31B | |
|---|---|---|
| Provider | Anthropic | |
| Input $/1M | $1.00 | $0.100 |
| Output $/1M | $5.00 | $0.340 |
| Blended $/1M | $2.00 | $0.160 |
| Context window | 200K | 262K |
| Max output | 64K | 262K |
| Released | Oct 2025 | Apr 2026 |
| Licence | Proprietary | Open weights |
| GPQA Diamond | 71.2% | 75.8% |
| SimpleQA Verified | 5.9% | 9.6% |
| OTIS Mock AIME | 66.7% | 73.3% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Claude Haiku 4.5 if…
- No clear advantage on the data we hold.
Choose Gemma 4 31B if…
- Costs less per token — $0.160 vs $2.00 blended
- Higher GPQA Diamond (75.8% vs 71.2%)
- Higher SimpleQA Verified (9.6% vs 5.9%)
- Higher OTIS Mock AIME (73.3% vs 66.7%)
- Larger context window (262K)
- Open weights — self-hostable
- Newer model (released Apr 2026)
FAQ
Which is better, Claude Haiku 4.5 or Gemma 4 31B?
Across the 3 benchmarks both models have independently-run scores for, Claude Haiku 4.5 leads on 0 and Gemma 4 31B leads on 3. Benchmarks are one input — price and context window are on this page too.
Is Claude Haiku 4.5 cheaper than Gemma 4 31B?
Gemma 4 31B is cheaper: $0.160 versus $2.00 per million tokens blended at 3:1 input:output. Input alone: $1.00 vs $0.100. Output alone: $5.00 vs $0.340.
What context windows do Claude Haiku 4.5 and Gemma 4 31B have?
Claude Haiku 4.5: 200,000 tokens. Gemma 4 31B: 262,144 tokens.
Who makes Claude Haiku 4.5 and Gemma 4 31B?
Claude Haiku 4.5 is made by Anthropic. Gemma 4 31B is made by Google.
Related comparisons