# GPT-4.1 mini vs Llama 2-70B

> GPT-4.1 mini is the stronger model overall, scoring 33.5 to 24.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-1-mini-vs-llama-2-70b
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. GPT-4.1 mini scores higher in 5 categories and Llama 2-70B in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-4.1 mini leads 34.7 to 7.4.
- The biggest single-benchmark swing is MATH Level 5: 87.3% for GPT-4.1 mini and 3.3% for Llama 2-70B.
- Llama 2-70B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4.1 mini | Llama 2-70B |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 33.5 | 24.1 |
| Rank | 232 | 343 |
| Context | 1.05M | — |
| Input $/M | $0.40 | — |
| Output $/M | $1.60 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-4.1 mini: 30.4 (#286)
- Llama 2-70B: 30.8 (#281)

| Benchmark | GPT-4.1 mini | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1367 | 1079 |
| SWE-bench Verified (bash only) | 23.9% | — |
| Aider Polyglot | 32.4% | — |
| SciCode | 40.4% | — |
| WeirdML | 37.6% | — |
| BigCodeBench Instruct | 48.9% | — |
| CadEval | 16% | — |

## Agentic & Tool Use

- GPT-4.1 mini: 33.0 (#52)
- Llama 2-70B: —

| Benchmark | GPT-4.1 mini | Llama 2-70B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | — |

## Reasoning

- GPT-4.1 mini: 10.9 (#335)
- Llama 2-70B: 13.7 (#324)

| Benchmark | GPT-4.1 mini | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1349 | 1073 |
| DTBench | 68.8% | 41.6% |
| Epoch Capabilities Index | 135.01 | 113.59 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 48.6% | — |
| ARC-AGI-1 | 3.5% | — |
| CritPt | 0% | — |
| Chess Puzzles | 7% | — |
| Mystery Game Puzzles | 7% | — |
| LMCA | 21.1% | — |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |

## Math

- GPT-4.1 mini: 23.1 (#264)
- Llama 2-70B: 7.5 (#320)

| Benchmark | GPT-4.1 mini | Llama 2-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 44.7% | 0% |
| LMArena Math | 1343 | 1091 |
| MATH Level 5 | 87.3% | 3.3% |
| FrontierMath (Tiers 1-3) | 6.7% | — |
| Omni-MATH | 49.1% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |
| GSM8K | — | 69.6% |

## Knowledge

- GPT-4.1 mini: 34.7 (#183)
- Llama 2-70B: 7.4 (#305)

| Benchmark | GPT-4.1 mini | Llama 2-70B |
|---|---|---|
| GPQA Diamond | 65.8% | 26.3% |
| LMArena Expert | 1338 | 1039 |
| SimpleQA Verified | 12.7% | — |
| MMLU-Pro | 78.3% | — |
| GPQA (HELM) | 61.4% | — |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |

## Multimodal

- GPT-4.1 mini: 35.2 (#77)
- Llama 2-70B: —

| Benchmark | GPT-4.1 mini | Llama 2-70B |
|---|---|---|
| LMArena Vision | 1181 | — |

## Multilingual

- GPT-4.1 mini: 45.9 (#161)
- Llama 2-70B: 27.9 (#269)

| Benchmark | GPT-4.1 mini | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1318 | 1045 |
| LMArena Chinese | 1329 | 994 |
| LMArena French | 1357 | 1089 |
| LMArena German | 1349 | 1041 |
| LMArena Japanese | 1291 | 927 |
| LMArena Korean | 1298 | 964 |
| LMArena Russian | 1324 | 1083 |
| LMArena Spanish | 1319 | 1142 |

## Instruction Following

- GPT-4.1 mini: 73.9 (#113)
- Llama 2-70B: 55.1 (#273)

| Benchmark | GPT-4.1 mini | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1332 | 1071 |
| IFEval | 90.4% | — |

## Long Context

- GPT-4.1 mini: 31.8 (#270)
- Llama 2-70B: 32.2 (#265)

| Benchmark | GPT-4.1 mini | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1344 | 1062 |
| Fiction.LiveBench | 44.4% | — |

## Writing & Preference

- GPT-4.1 mini: 48.8 (#193)
- Llama 2-70B: 32.5 (#274)

| Benchmark | GPT-4.1 mini | Llama 2-70B |
|---|---|---|
| LMArena Text | 1341 | 1115 |
| LMArena Creative Writing | 1300 | 1075 |
| LMArena Multi-Turn | 1354 | 1088 |
| EQ-Bench Creative Writing | 1147 | — |
| WildBench | 83.8% | — |

## FAQ

### Is GPT-4.1 mini better than Llama 2-70B?

GPT-4.1 mini is the stronger model overall, scoring 33.5 to 24.1 on the Noometry Index.

### Is GPT-4.1 mini or Llama 2-70B better for coding?

They score almost the same on coding (30.4 vs 30.8); test both on your own repository before choosing.

### How many benchmarks do GPT-4.1 mini and Llama 2-70B share?

22 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Llama 2-70B has 35.