Model comparison
GPT-5.1 vs Llama 2-70B
GPT-5.1 is the stronger model overall, scoring 49.0 to 24.4 on the Noometry Index.
Last verified . 22 shared benchmarks.
MetaSummary
- They share 22 benchmarks with published results for both. GPT-5.1 scores higher in 8 categories and Llama 2-70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.1 leads 52.2 to 8.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.6% for GPT-5.1 and 0% for Llama 2-70B.
- Llama 2-70B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.1 | Llama 2-70B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 49.0 | 24.4 |
| Released | 2025-11-13 | 2023-07-18 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 63 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
GPT-5.1: 46.4 (#66), Llama 2-70B: 31.4 (#286)
| Benchmark | GPT-5.1 | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1454 | 1079 |
| SWE-bench Verified | 68% | — |
| SWE-bench Verified (bash only) | 66% | — |
| LMArena WebDev | 1395 | — |
| SciCode | 43.3% | — |
| GSO | 13.7% | — |
| WeirdML | 60.8% | — |
| LiveBench Coding | 72.5% | — |
| ALE-Bench | 1,192 | — |
Agentic & Tool Use Not comparable
GPT-5.1: 32.7 (#60), Llama 2-70B: —
| Benchmark | GPT-5.1 | Llama 2-70B |
|---|---|---|
| Terminal-Bench | 47.6% | — |
| DeepResearch Bench | 42.8% | — |
| LMArena Search | 1199 | — |
| Vending-Bench 2 | 1,473 | — |
Reasoning GPT-5.1 leads
GPT-5.1: 39.8 (#58), Llama 2-70B: 14.4 (#325)
| Benchmark | GPT-5.1 | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1457 | 1073 |
| DTBench | 90.1% | 41.6% |
| Epoch Capabilities Index | 149.64 | 113.79 |
| ForecastBench | 58.1 | 51.4 |
| ARC-AGI-2 | 17.6% | — |
| SimpleBench | 53.2% | — |
| ARC-AGI-1 | 72.8% | — |
| CritPt | 4.9% | — |
| Chess Puzzles | 32% | — |
| EnigmaEval | 11.2% | — |
| LiveBench Reasoning | 95.8% | — |
| Mystery Game Puzzles | 19% | — |
| LiveBench Data Analysis | 72.1% | — |
| LMCA | 43.9% | — |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| LiveBench | 78.8% | — |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |
Math GPT-5.1 leads
GPT-5.1: 52.2 (#51), Llama 2-70B: 8.1 (#326)
| Benchmark | GPT-5.1 | Llama 2-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.6% | 0% |
| LMArena Math | 1447 | 1091 |
| Omni-MATH | 46.4% | — |
| LiveBench Math | 94.5% | — |
| MATH Level 5 | — | 3.3% |
| FrontierMath (Feb 2025 set) | 31% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
| GSM8K | — | 69.6% |
Knowledge GPT-5.1 leads
GPT-5.1: 50.6 (#71), Llama 2-70B: 7.4 (#310)
| Benchmark | GPT-5.1 | Llama 2-70B |
|---|---|---|
| GPQA Diamond | 87.6% | 26.3% |
| LMArena Expert | 1470 | 1039 |
| Humanity's Last Exam | 23.7% | — |
| SimpleQA Verified | 48% | — |
| MMLU-Pro | 57.9% | — |
| Vectara Hallucination Rate | 10.9% | — |
| GPQA (HELM) | 44.2% | — |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |
Multimodal Not comparable
GPT-5.1: 44.8 (#19), Llama 2-70B: —
| Benchmark | GPT-5.1 | Llama 2-70B |
|---|---|---|
| LMArena Vision | 1250 | — |
| VPCT | 58.7% | — |
| LMArena Document | 1403 | — |
Multilingual GPT-5.1 leads
GPT-5.1: 53.8 (#56), Llama 2-70B: 27.7 (#274)
| Benchmark | GPT-5.1 | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1431 | 1045 |
| LMArena Chinese | 1495 | 995 |
| LMArena French | 1450 | 1090 |
| LMArena German | 1438 | 1041 |
| LMArena Japanese | 1453 | 927 |
| LMArena Korean | 1401 | 964 |
| LMArena Russian | 1435 | 1083 |
| LMArena Spanish | 1433 | 1143 |
Instruction Following GPT-5.1 leads
GPT-5.1: 83.9 (#1), Llama 2-70B: 54.9 (#278)
| Benchmark | GPT-5.1 | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1443 | 1071 |
| LiveBench Instruction Following | 93.3% | — |
| IFEval | 93.5% | — |
Long Context GPT-5.1 leads
GPT-5.1: 47.6 (#14), Llama 2-70B: 32.3 (#270)
| Benchmark | GPT-5.1 | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1447 | 1062 |
| CL-bench | 23.7% | — |
| CL-bench Life | 17.3% | — |
Writing & Preference GPT-5.1 leads
GPT-5.1: 64.5 (#55), Llama 2-70B: 32.3 (#279)
| Benchmark | GPT-5.1 | Llama 2-70B |
|---|---|---|
| LMArena Text | 1443 | 1115 |
| LMArena Creative Writing | 1427 | 1075 |
| LMArena Multi-Turn | 1450 | 1088 |
| WildBench | 86.3% | — |
| LiveBench Language | 80.2% | — |
Frequently asked questions
Is GPT-5.1 better than Llama 2-70B?
GPT-5.1 is the stronger model overall, scoring 49.0 to 24.4 on the Noometry Index.
Is GPT-5.1 or Llama 2-70B better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.4 versus 31.4 in the Noometry coding category.
How many benchmarks do GPT-5.1 and Llama 2-70B share?
22 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and Llama 2-70B has 35.