# Claude Haiku 4.5 vs GPT-5.1-Codex

> Side-by-side benchmark comparison for Claude Haiku 4.5 and GPT-5.1-Codex across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-haiku-4-5-vs-gpt-5-1-codex
- Last updated: September 29, 2026

- Shared sourced benchmarks: 2
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.7

## Quick Verdict

Evidence is too thin for a benchmark verdict: Claude Haiku 4.5 and GPT-5.1-Codex share only 2 sourced benchmark rows.

## Summary

- Only 2 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Claude Haiku 4.5 has the lower published output-token price.
- GPT-5.1-Codex has the larger published context window at 400K.

## Model Snapshot

| Property | Claude Haiku 4.5 | GPT-5.1-Codex |
|----------|----------|----------|
| Creator | Anthropic | OpenAI |
| Type | Proprietary | Proprietary |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 200K | 400K |
| Independent public score (not head-to-head) | 42.47 | 44.38 |
| Benchmarks Covered | 10 | 4 |
| Pricing (input/output) | $1.00 / $5.00 | $1.25 / $10.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Claude Haiku 4.5 public-lane score: 22 (Supported · #96/117)
- GPT-5.1-Codex public-lane score: Coming soon

| Benchmark | Claude Haiku 4.5 | GPT-5.1-Codex | Winner |
|-----------|-----------|-----------|--------|
| JobBench | 16.0% | 26.2% | GPT-5.1-Codex |
| Terminal-Bench 2.1 (Vals) | 43.8% | Coming soon | Coming soon |
| Gert Labs | Coming soon | 49.68% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Claude Haiku 4.5 public-lane score: 19.6 (Supported · #124/143)
- GPT-5.1-Codex public-lane score: 32.7 (Estimated · #85/143)

| Benchmark | Claude Haiku 4.5 | GPT-5.1-Codex | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 73.3% | Coming soon | Coming soon |
| VulcanBench v3 | 76.2% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 41.2% | 85.6% | GPT-5.1-Codex |
| SWE-bench (Vals) | 66.6% | Coming soon | Coming soon |
| Vibe Code Bench | Coming soon | 13.12% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Claude Haiku 4.5 public-lane score: Coming soon
- GPT-5.1-Codex public-lane score: 69.9 (Unranked · 2 rankable rows)

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Claude Haiku 4.5 public-lane score: Coming soon
- GPT-5.1-Codex public-lane score: 67.9 (Unranked · 1 rankable row)

### Knowledge

- Winner: Insufficient shared evidence
- Claude Haiku 4.5 public-lane score: 34.8 (Estimated · #119/169)
- GPT-5.1-Codex public-lane score: 48.1 (Estimated · #69/169)

| Benchmark | Claude Haiku 4.5 | GPT-5.1-Codex | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond (Vals) | 72.2% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 78.7% | Coming soon | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Claude Haiku 4.5 public-lane score: Coming soon
- GPT-5.1-Codex public-lane score: 84.2 (#42/124)

### Mathematics

- Winner: Insufficient shared evidence
- Claude Haiku 4.5 public-lane score: 28.8 (Unranked · 2 rankable rows)
- GPT-5.1-Codex public-lane score: Coming soon

| Benchmark | Claude Haiku 4.5 | GPT-5.1-Codex | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 5.903% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 2.083% | Coming soon | Coming soon |

## FAQ

### Is there enough evidence to pick between Claude Haiku 4.5 and GPT-5.1-Codex?

Not yet. The models share only 2 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [Claude Haiku 4.5 vs Claude Haiku 4.5 Thinking](/compare/claude-haiku-4-5-vs-claude-haiku-4-5-thinking)
- [GPT-5.1-Codex vs Claude Haiku 4.5 Thinking](/compare/claude-haiku-4-5-thinking-vs-gpt-5-1-codex)
- [Claude Haiku 4.5 vs GPT-6 Astra](/compare/claude-haiku-4-5-vs-gpt-6-astra)
- [GPT-5.1-Codex vs GPT-6 Astra](/compare/gpt-5-1-codex-vs-gpt-6-astra)

## Explore More

- [Claude Haiku 4.5 profile](/models/claude-haiku-4-5)
- [GPT-5.1-Codex profile](/models/gpt-5-1-codex)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)