Claude Haiku 4.5 Turbo vs Mistral Large 3 Instruct: which model should you choose?
We compared Claude Haiku 4.5 Turbo and Mistral Large 3 Instruct on price, context window and 12 benchmarks. Mistral Large 3 Instruct has the stronger average benchmark score; Mistral Large 3 Instruct is cheaper on a blended 3:1 basis.
Claude Haiku 4.5 Turbo
Claude Haiku 4.5 Turbo is a multimodal model from Anthropic. It offers a 200,000-token context window, costs $14.37 per million input tokens and $54.76 per million output tokens, and averages 80.0 across the index's benchmark suite.
- Input
- $14.37 / 1M
- Output
- $54.76 / 1M
- Context
- 200,000
- Avg score
- 80.0
- Open weights
- No
Mistral Large 3 Instruct
Mistral Large 3 Instruct is a multimodal model from Mistral AI. It offers a 400,000-token context window, costs $5.31 per million input tokens and $22.47 per million output tokens, and averages 81.1 across the index's benchmark suite.
- Input
- $5.31 / 1M
- Output
- $22.47 / 1M
- Context
- 400,000
- Avg score
- 81.1
- Open weights
- Yes
Specification comparison
| Spec | Claude Haiku 4.5 Turbo | Mistral Large 3 Instruct | Edge |
|---|---|---|---|
| Input price / 1M | $14.37 | $5.31 | B |
| Output price / 1M | $54.76 | $22.47 | B |
| Context window | 200,000 | 400,000 | B |
| Max output | 32,768 | 65,536 | B |
| Average score | 80.0 | 81.1 | B |
| Arena Elo | 1434.5 | 1446.2 | B |
| Open weights | No | Yes | B |
Benchmark comparison
Claude Haiku 4.5 Turbo wins 4, Mistral Large 3 Instruct wins 8, and 0 benchmarks are tied. The table shows the modelled score for each model and the gap.
| Benchmark | Claude Haiku 4.5 Turbo | Mistral Large 3 Instruct | Gap | Winner |
|---|---|---|---|---|
| MMLU-Pro | 80.6 | 82.3 | 1.7 | Mistral Large 3 Instruct |
| GPQA Diamond | 75.1 | 79.8 | 4.7 | Mistral Large 3 Instruct |
| SWE-bench Verified | 68.4 | 71.9 | 3.5 | Mistral Large 3 Instruct |
| HumanEval | 87.0 | 84.2 | 2.8 | Claude Haiku 4.5 Turbo |
| MATH-500 | 83.7 | 83.4 | 0.3 | Claude Haiku 4.5 Turbo |
| AIME 2025 | 79.2 | 76.2 | 3.0 | Claude Haiku 4.5 Turbo |
| LiveCodeBench | 71.7 | 75.1 | 3.4 | Mistral Large 3 Instruct |
| IFEval | 87.1 | 87.6 | 0.5 | Mistral Large 3 Instruct |
| TruthfulQA | 81.0 | 85.5 | 4.5 | Mistral Large 3 Instruct |
| HellaSwag | 88.1 | 89.1 | 1.0 | Mistral Large 3 Instruct |
| MMMU | 77.7 | 76.5 | 1.2 | Claude Haiku 4.5 Turbo |
| Arena Elo | 1434.5 | 1446.2 | 11.7 | Mistral Large 3 Instruct |
Price analysis
On a blended 3:1 input-to-output basis, Claude Haiku 4.5 Turbo costs about $24.47 per million tokens and Mistral Large 3 Instruct costs about $9.60. Mistral Large 3 Instruct is roughly 61% cheaper than Claude Haiku 4.5 Turbo. At high volume, that gap compounds quickly, so price should carry real weight unless the quality difference is decisive.
Mistral Large 3 Instruct has the larger context window at 400,000 tokens, compared with 200,000 for Claude Haiku 4.5 Turbo. That matters for long documents, large codebases and multi-step agent traces.
Verdict
Across 12 shared benchmarks, Claude Haiku 4.5 Turbo wins 4, Mistral Large 3 Instruct wins 8, and 0 are tied. On the index average, Mistral Large 3 Instruct leads Claude Haiku 4.5 Turbo by 1.1 points (81.1 versus 80.0).
The price picture favours Mistral Large 3 Instruct. The context picture favours Mistral Large 3 Instruct. Those two dimensions often matter more than a few benchmark points once a model is good enough for the task.
If you need a single default, start with Mistral Large 3 Instruct for quality-sensitive work, and check whether its price holds at your expected volume before committing.
Choose Claude Haiku 4.5 Turbo if
- You prefer Anthropic's tooling or already use it.
Choose Mistral Large 3 Instruct if
- You want the higher average benchmark score in this index.
- Unit cost matters and you want the cheaper blended price.
- You need the larger 400,000-token context window.
- You need the larger 65,536-token output limit.
FAQ
Is Claude Haiku 4.5 Turbo better than Mistral Large 3 Instruct?
On the index average, Mistral Large 3 Instruct leads Claude Haiku 4.5 Turbo by 1.1 points (81.1 versus 80.0). The better choice depends on price, context and your task. Claude Haiku 4.5 Turbo wins 4 benchmarks, Mistral Large 3 Instruct wins 8.
Which is cheaper, Claude Haiku 4.5 Turbo or Mistral Large 3 Instruct?
Mistral Large 3 Instruct is cheaper on a blended 3:1 basis at about $9.60 per million tokens, versus $24.47 for Claude Haiku 4.5 Turbo.
Which has the larger context window?
Mistral Large 3 Instruct has the larger context window at 400,000 tokens. Claude Haiku 4.5 Turbo has 200,000 tokens.
Are these models open weights?
Claude Haiku 4.5 Turbo is proprietary; Mistral Large 3 Instruct is open weights.
Which should I choose for production?
If you need a single default, start with Mistral Large 3 Instruct for quality-sensitive work, and check whether its price holds at your expected volume before committing.