# Claude 2.1 vs GPT-5.4 mini

> GPT-5.4 mini is the stronger model overall, scoring 44.8 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-1-vs-gpt-5-4-mini
- Last updated: 2026-10-10
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both. Claude 2.1 scores higher in 0 categories and GPT-5.4 mini in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 mini leads 51.4 to 15.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.9% for Claude 2.1 and 88.9% for GPT-5.4 mini.

## Snapshot

| | Claude 2.1 | GPT-5.4 mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 24.9 | 44.8 |
| Rank | 340 | 69 |
| Context | — | 400K |
| Input $/M | — | $0.75 |
| Output $/M | — | $4.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 2.1: 25.8 (#322)
- GPT-5.4 mini: 45.0 (#67)

| Benchmark | Claude 2.1 | GPT-5.4 mini |
|---|---|---|
| WeirdML | 7.1% | 60.3% |
| FrontierCode | — | 27% |
| LMArena WebDev | — | 1397 |
| SciCode | — | 49.9% |
| LMArena Coding | — | 1438 |
| ALE-Bench | — | 1,189 |

## Agentic & Tool Use

- Claude 2.1: —
- GPT-5.4 mini: 29.6 (#74)

| Benchmark | Claude 2.1 | GPT-5.4 mini |
|---|---|---|
| DeepResearch Bench | — | 36.3% |

## Reasoning

- Claude 2.1: 20.6 (#216)
- GPT-5.4 mini: 30.3 (#77)

| Benchmark | Claude 2.1 | GPT-5.4 mini |
|---|---|---|
| DTBench | 51% | 80% |
| Epoch Capabilities Index | 119.22 | 148.83 |
| ForecastBench | 54.2 | 57 |
| ARC-AGI-2 | — | 18.9% |
| Kagi LLM Benchmark | — | 37.9% |
| NYT Connections (extended) | — | 61.8% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | — | 10% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 61.7% |
| LMArena Hard Prompts | — | 1424 |
| Mystery Game Puzzles | — | 11% |
| LMCA | — | 40.8% |

## Math

- Claude 2.1: 9.6 (#309)
- GPT-5.4 mini: 45.4 (#63)

| Benchmark | Claude 2.1 | GPT-5.4 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | 88.9% |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 9.8% |
| ProofBench | — | 21% |
| LMArena Math | — | 1418 |
| FrontierMath (Feb 2025 set) | — | 28.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Claude 2.1: 15.5 (#287)
- GPT-5.4 mini: 51.4 (#62)

| Benchmark | Claude 2.1 | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | 33% | 86.9% |
| SimpleQA Verified | — | 29.4% |
| Vectara Hallucination Rate | — | 5.5% |
| LMArena Expert | — | 1434 |
| MMLU | 73.5% | — |

## Multimodal

- Claude 2.1: —
- GPT-5.4 mini: 39.0 (#51)

| Benchmark | Claude 2.1 | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | — | 1245 |

## Multilingual

- Claude 2.1: —
- GPT-5.4 mini: 52.1 (#94)

| Benchmark | Claude 2.1 | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | — | 1405 |
| LMArena Chinese | — | 1446 |
| LMArena French | — | 1440 |
| LMArena German | — | 1407 |
| LMArena Japanese | — | 1375 |
| LMArena Korean | — | 1369 |
| LMArena Russian | — | 1417 |
| LMArena Spanish | — | 1403 |

## Instruction Following

- Claude 2.1: —
- GPT-5.4 mini: 74.3 (#99)

| Benchmark | Claude 2.1 | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | — | 1405 |

## Long Context

- Claude 2.1: —
- GPT-5.4 mini: 42.9 (#107)

| Benchmark | Claude 2.1 | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | — | 1407 |

## Writing & Preference

- Claude 2.1: —
- GPT-5.4 mini: 64.2 (#56)

| Benchmark | Claude 2.1 | GPT-5.4 mini |
|---|---|---|
| LMArena Text | — | 1411 |
| LMArena Creative Writing | — | 1370 |
| EQ-Bench Creative Writing | — | 1665 |
| LMArena Multi-Turn | — | 1429 |

## FAQ

### Is Claude 2.1 better than GPT-5.4 mini?

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 24.9 on the Noometry Index.

### Is Claude 2.1 or GPT-5.4 mini better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 25.8 in the Noometry coding category.

### How many benchmarks do Claude 2.1 and GPT-5.4 mini share?

6 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and GPT-5.4 mini has 46.