# Claude Haiku 5.5 vs GPT-5 Nano

> Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 33.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-haiku-5-5-vs-gpt-5-nano
- Last updated: 2026-10-10
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both. Claude Haiku 5.5 scores higher in 5 categories and GPT-5 Nano in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 5.5 leads 73.6 to 29.4.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 75.1% for Claude Haiku 5.5 and 20% for GPT-5 Nano.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $0.10 / $0.50 for Claude Haiku 5.5.
- Claude Haiku 5.5 accepts more context: 1M tokens versus 400K.

## Snapshot

| | Claude Haiku 5.5 | GPT-5 Nano |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 49.5 | 33.5 |
| Rank | 52 | 241 |
| Context | 1M | 400K |
| Input $/M | $0.10 | $0.05 |
| Output $/M | $0.50 | $0.40 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Haiku 5.5: 49.2 (#50)
- GPT-5 Nano: 33.6 (#254)

| Benchmark | Claude Haiku 5.5 | GPT-5 Nano |
|---|---|---|
| SWE-bench Verified (bash only) | — | 34.8% |
| LMArena WebDev | 1587 | — |
| WeirdML | — | 38.1% |
| LMArena Coding | — | 1351 |
| ALE-Bench | — | 718.67 |

## Agentic & Tool Use

- Claude Haiku 5.5: —
- GPT-5 Nano: 25.8 (#106)

| Benchmark | Claude Haiku 5.5 | GPT-5 Nano |
|---|---|---|
| Terminal-Bench | — | 21.8% |
| Berkeley Function Calling Leaderboard | — | 51.5% |

## Reasoning

- Claude Haiku 5.5: 35.2 (#69)
- GPT-5 Nano: 16.3 (#306)

| Benchmark | Claude Haiku 5.5 | GPT-5 Nano |
|---|---|---|
| Mystery Game Puzzles | 30% | 9% |
| ARC-AGI-2 | — | 2.6% |
| Kagi LLM Benchmark | — | 62.2% |
| NYT Connections (extended) | 65.7% | — |
| ARC-AGI-1 | — | 20.7% |
| Chess Puzzles | — | 27% |
| LMArena Hard Prompts | — | 1328 |
| DTBench | — | 62.7% |
| LMCA | — | 7.9% |
| Epoch Capabilities Index | — | 139.38 |
| ForecastBench | — | 59.1 |

## Math

- Claude Haiku 5.5: 73.6 (#18)
- GPT-5 Nano: 29.4 (#241)

| Benchmark | Claude Haiku 5.5 | GPT-5 Nano |
|---|---|---|
| FrontierMath (Tiers 1-3) | 75.1% | 20% |
| FrontierMath Tier 4 | 46.3% | 2.4% |
| OTIS Mock AIME 2024-2025 | 98.9% | 81.1% |
| ProofBench | — | 12% |
| Omni-MATH | — | 54.6% |
| LMArena Math | — | 1317 |
| MATH Level 5 | — | 95.2% |
| FrontierMath (Feb 2025 set) | — | 8.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Claude Haiku 5.5: 50.8 (#70)
- GPT-5 Nano: 35.9 (#178)

| Benchmark | Claude Haiku 5.5 | GPT-5 Nano |
|---|---|---|
| GPQA Diamond | 89.6% | 69.4% |
| SimpleQA Verified | 23.8% | 11.7% |
| MMLU-Pro | — | 77.8% |
| Vectara Hallucination Rate | — | 10.5% |
| GPQA (HELM) | — | 67.9% |
| LMArena Expert | — | 1321 |

## Multimodal

- Claude Haiku 5.5: 43.7 (#21)
- GPT-5 Nano: 31.3 (#108)

| Benchmark | Claude Haiku 5.5 | GPT-5 Nano |
|---|---|---|
| LMArena Vision | — | 1159 |
| VPCT | — | 37.2% |
| Furniture Assembly | 47.5% | — |

## Multilingual

- Claude Haiku 5.5: —
- GPT-5 Nano: 45.3 (#172)

| Benchmark | Claude Haiku 5.5 | GPT-5 Nano |
|---|---|---|
| LMArena Non-English | — | 1313 |
| LMArena Chinese | — | 1356 |
| LMArena German | — | 1327 |
| LMArena Japanese | — | 1226 |
| LMArena Korean | — | 1269 |
| LMArena Russian | — | 1296 |
| LMArena Spanish | — | 1360 |

## Instruction Following

- Claude Haiku 5.5: —
- GPT-5 Nano: 75.0 (#79)

| Benchmark | Claude Haiku 5.5 | GPT-5 Nano |
|---|---|---|
| IFEval | — | 93.2% |
| LMArena Instruction Following | — | 1306 |

## Long Context

- Claude Haiku 5.5: —
- GPT-5 Nano: 31.3 (#281)

| Benchmark | Claude Haiku 5.5 | GPT-5 Nano |
|---|---|---|
| Fiction.LiveBench | — | 44.4% |
| LMArena Longer Query | — | 1312 |

## Writing & Preference

- Claude Haiku 5.5: —
- GPT-5 Nano: 39.1 (#249)

| Benchmark | Claude Haiku 5.5 | GPT-5 Nano |
|---|---|---|
| LMArena Text | — | 1320 |
| LMArena Creative Writing | — | 1249 |
| EQ-Bench Creative Writing | — | 705 |
| WildBench | — | 80.6% |
| LMArena Multi-Turn | — | 1311 |

## FAQ

### Is Claude Haiku 5.5 better than GPT-5 Nano?

Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 33.5 on the Noometry Index.

### Which is cheaper, Claude Haiku 5.5 or GPT-5 Nano?

GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Claude Haiku 5.5 lists at $0.10 and $0.50.

### Is Claude Haiku 5.5 or GPT-5 Nano better for coding?

Claude Haiku 5.5 scores higher on coding benchmarks: 49.2 versus 33.6 in the Noometry coding category.

### Which has the bigger context window?

Claude Haiku 5.5 does, with 1M tokens against 400K.

### How many benchmarks do Claude Haiku 5.5 and GPT-5 Nano share?

6 benchmarks have published results for both models. Claude Haiku 5.5 has 9 scored results on Noometry and GPT-5 Nano has 49.