Model comparison
Claude Haiku 5.5 vs Codestral
Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 30.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in coding, where Claude Haiku 5.5 leads 49.2 to 27.3.
- Claude Haiku 5.5 is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Claude Haiku 5.5 accepts more context: 1M tokens versus 256K.
Side by side
| Claude Haiku 5.5 | Codestral | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 49.5 | 30.6 |
| Released | 2026-10-07 | 2024-05-29 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 256K |
| Max output | 128K | 8K |
| Input $ / M tokens | $0.10 | $0.30 |
| Output $ / M tokens | $0.50 | $0.90 |
| Results tracked | 9 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 5.5 leads
Claude Haiku 5.5: 49.2 (#50), Codestral: 27.3 (#321)
| Benchmark | Claude Haiku 5.5 | Codestral |
|---|---|---|
| Aider Polyglot | — | 11.1% |
| LMArena WebDev | 1587 | — |
| BigCodeBench Instruct | — | 41.8% |
| BigCodeBench Complete | — | 52.5% |
| ALE-Bench | — | 137.78 |
| HumanEval+ | — | 73.8% |
| MBPP+ | — | 61.9% |
Reasoning Claude Haiku 5.5 leads
Claude Haiku 5.5: 35.2 (#69), Codestral: 19.8 (#251)
| Benchmark | Claude Haiku 5.5 | Codestral |
|---|---|---|
| Kagi LLM Benchmark | — | 32.5% |
| NYT Connections (extended) | 65.7% | — |
| Mystery Game Puzzles | 30% | — |
Math Not comparable
Claude Haiku 5.5: 73.6 (#18), Codestral: —
| Benchmark | Claude Haiku 5.5 | Codestral |
|---|---|---|
| FrontierMath (Tiers 1-3) | 75.1% | — |
| FrontierMath Tier 4 | 46.3% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |
Knowledge Not comparable
Claude Haiku 5.5: 50.8 (#70), Codestral: —
| Benchmark | Claude Haiku 5.5 | Codestral |
|---|---|---|
| GPQA Diamond | 89.6% | — |
| SimpleQA Verified | 23.8% | — |
Multimodal Not comparable
Claude Haiku 5.5: 43.7 (#21), Codestral: —
| Benchmark | Claude Haiku 5.5 | Codestral |
|---|---|---|
| Furniture Assembly | 47.5% | — |
Frequently asked questions
Is Claude Haiku 5.5 better than Codestral?
Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 30.6 on the Noometry Index.
Which is cheaper, Claude Haiku 5.5 or Codestral?
Claude Haiku 5.5 is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Codestral lists at $0.30 and $0.90.
Is Claude Haiku 5.5 or Codestral better for coding?
Claude Haiku 5.5 scores higher on coding benchmarks: 49.2 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
Claude Haiku 5.5 does, with 1M tokens against 256K.
How many benchmarks do Claude Haiku 5.5 and Codestral share?
0 benchmarks have published results for both models. Claude Haiku 5.5 has 9 scored results on Noometry and Codestral has 7.