# Claude Haiku 5.5 vs GPT-5

> GPT-5 is the stronger model overall, scoring 50.9 to 49.5 on the Noometry Index. Claude Haiku 5.5 costs 17× less per token, which makes it the better buy when GPT-5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-haiku-5-5-vs-gpt-5
- Last updated: 2026-10-10
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both. Claude Haiku 5.5 scores higher in 1 category and GPT-5 in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 5.5 leads 73.6 to 55.0.
- The biggest single-benchmark swing is SimpleQA Verified: 23.8% for Claude Haiku 5.5 and 50.1% for GPT-5.
- Claude Haiku 5.5 is cheaper at $0.10 / $0.50 per million input/output tokens, against $1.25 / $10 for GPT-5.
- Claude Haiku 5.5 accepts more context: 1M tokens versus 400K.

## Snapshot

| | Claude Haiku 5.5 | GPT-5 |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 49.5 | 50.9 |
| Rank | 52 | 45 |
| Context | 1M | 400K |
| Input $/M | $0.10 | $1.25 |
| Output $/M | $0.50 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Haiku 5.5: 49.2 (#50)
- GPT-5: 50.3 (#47)

| Benchmark | Claude Haiku 5.5 | GPT-5 |
|---|---|---|
| LMArena WebDev | 1587 | 1418 |
| SWE-bench Verified | — | 73.6% |
| SWE-bench Verified (bash only) | — | 65% |
| Aider Polyglot | — | 88% |
| SciCode | — | 42.9% |
| GSO | — | 6.9% |
| WeirdML | — | 60.7% |
| LMArena Coding | — | 1436 |
| ALE-Bench | — | 1,162 |
| AlgoTune | — | 1.67 |

## Agentic & Tool Use

- Claude Haiku 5.5: —
- GPT-5: 33.1 (#56)

| Benchmark | Claude Haiku 5.5 | GPT-5 |
|---|---|---|
| Terminal-Bench | — | 49.6% |
| GDPval | — | 34.8% |
| Remote Labor Index | — | 1.7% |
| DeepResearch Bench | — | 49.6% |
| BALROG | — | 32.8% |
| LMArena Search | — | 1133 |
| METR Time Horizons | — | 69.6% |

## Reasoning

- Claude Haiku 5.5: 35.2 (#69)
- GPT-5: 38.3 (#64)

| Benchmark | Claude Haiku 5.5 | GPT-5 |
|---|---|---|
| Mystery Game Puzzles | 30% | 23% |
| ARC-AGI-2 | — | 9.9% |
| SimpleBench | — | 56.7% |
| Kagi LLM Benchmark | — | 72.7% |
| NYT Connections (extended) | 65.7% | — |
| ARC-AGI-1 | — | 65.7% |
| CritPt | — | 12.6% |
| Chess Puzzles | — | 37% |
| EnigmaEval | — | 10.5% |
| EBR-Bench | — | 12.7% |
| LMArena Hard Prompts | — | 1416 |
| DTBench | — | 90.7% |
| LMCA | — | 40% |
| Epoch Capabilities Index | — | 150 |
| ForecastBench | — | 61.4 |

## Math

- Claude Haiku 5.5: 73.6 (#18)
- GPT-5: 55.0 (#44)

| Benchmark | Claude Haiku 5.5 | GPT-5 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 75.1% | 55.4% |
| FrontierMath Tier 4 | 46.3% | 22% |
| OTIS Mock AIME 2024-2025 | 98.9% | 91.4% |
| ProofBench | — | 18% |
| Omni-MATH | — | 64.7% |
| LMArena Math | — | 1407 |
| MATH Level 5 | — | 98.1% |
| FrontierMath (Feb 2025 set) | — | 32.4% |
| FrontierMath Tier 4 (v1) | — | 12.5% |

## Knowledge

- Claude Haiku 5.5: 50.8 (#70)
- GPT-5: 56.6 (#43)

| Benchmark | Claude Haiku 5.5 | GPT-5 |
|---|---|---|
| GPQA Diamond | 89.6% | 86.2% |
| SimpleQA Verified | 23.8% | 50.1% |
| Humanity's Last Exam | — | 25.3% |
| MMLU-Pro | — | 86.3% |
| Confabulations | — | 10.3% |
| Vectara Hallucination Rate | — | 14.7% |
| GPQA (HELM) | — | 79.2% |
| LMArena Expert | — | 1419 |

## Multimodal

- Claude Haiku 5.5: 43.7 (#21)
- GPT-5: 46.8 (#13)

| Benchmark | Claude Haiku 5.5 | GPT-5 |
|---|---|---|
| LMArena Vision | — | 1232 |
| GeoBench | — | 81% |
| VPCT | — | 66% |
| Furniture Assembly | 47.5% | — |

## Multilingual

- Claude Haiku 5.5: —
- GPT-5: 51.4 (#110)

| Benchmark | Claude Haiku 5.5 | GPT-5 |
|---|---|---|
| LMArena Non-English | — | 1397 |
| LMArena Chinese | — | 1422 |
| LMArena French | — | 1410 |
| LMArena German | — | 1416 |
| LMArena Japanese | — | 1409 |
| LMArena Korean | — | 1360 |
| LMArena Russian | — | 1406 |
| LMArena Spanish | — | 1399 |

## Instruction Following

- Claude Haiku 5.5: —
- GPT-5: 73.8 (#113)

| Benchmark | Claude Haiku 5.5 | GPT-5 |
|---|---|---|
| IFEval | — | 87.5% |
| LMArena Instruction Following | — | 1388 |

## Long Context

- Claude Haiku 5.5: —
- GPT-5: 69.5 (#2)

| Benchmark | Claude Haiku 5.5 | GPT-5 |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | — | 1399 |

## Writing & Preference

- Claude Haiku 5.5: —
- GPT-5: 63.4 (#65)

| Benchmark | Claude Haiku 5.5 | GPT-5 |
|---|---|---|
| LMArena Text | — | 1406 |
| LMArena Creative Writing | — | 1365 |
| Short-Story Creative Writing | — | 86% |
| EQ-Bench Creative Writing | — | 1627 |
| WildBench | — | 85.7% |
| LMArena Multi-Turn | — | 1426 |

## FAQ

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

GPT-5 is the stronger model overall, scoring 50.9 to 49.5 on the Noometry Index. Claude Haiku 5.5 costs 17× less per token, which makes it the better buy when GPT-5's lead doesn't matter for your workload.

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

Claude Haiku 5.5 is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; GPT-5 lists at $1.25 and $10.

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

GPT-5 scores higher on coding benchmarks: 50.3 versus 49.2 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 share?

7 benchmarks have published results for both models. Claude Haiku 5.5 has 9 scored results on Noometry and GPT-5 has 69.