Model comparison
GPT-5 Nano vs Llama 2-70B
GPT-5 Nano is the stronger model overall, scoring 33.5 to 24.4 on the Noometry Index.
Last verified . 22 shared benchmarks.
MetaSummary
- They share 22 benchmarks with published results for both. GPT-5 Nano scores higher in 7 categories and Llama 2-70B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5 Nano leads 35.9 to 7.4.
- The biggest single-benchmark swing is MATH Level 5: 95.2% for GPT-5 Nano and 3.3% for Llama 2-70B.
- Llama 2-70B has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Nano | Llama 2-70B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 33.5 | 24.4 |
| Released | 2025-08-07 | 2023-07-18 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 49 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Nano leads
GPT-5 Nano: 33.6 (#254), Llama 2-70B: 31.4 (#286)
| Benchmark | GPT-5 Nano | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1351 | 1079 |
| SWE-bench Verified (bash only) | 34.8% | — |
| WeirdML | 38.1% | — |
| ALE-Bench | 718.67 | — |
Agentic & Tool Use Not comparable
GPT-5 Nano: 25.8 (#106), Llama 2-70B: —
| Benchmark | GPT-5 Nano | Llama 2-70B |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
Reasoning GPT-5 Nano leads
GPT-5 Nano: 16.3 (#306), Llama 2-70B: 14.4 (#325)
| Benchmark | GPT-5 Nano | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1328 | 1073 |
| DTBench | 62.7% | 41.6% |
| Epoch Capabilities Index | 139.38 | 113.79 |
| ForecastBench | 59.1 | 51.4 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| Chess Puzzles | 27% | — |
| Mystery Game Puzzles | 9% | — |
| LMCA | 7.9% | — |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |
Math GPT-5 Nano leads
GPT-5 Nano: 29.4 (#241), Llama 2-70B: 8.1 (#326)
| Benchmark | GPT-5 Nano | Llama 2-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 81.1% | 0% |
| LMArena Math | 1317 | 1091 |
| MATH Level 5 | 95.2% | 3.3% |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
| GSM8K | — | 69.6% |
Knowledge GPT-5 Nano leads
GPT-5 Nano: 35.9 (#178), Llama 2-70B: 7.4 (#310)
| Benchmark | GPT-5 Nano | Llama 2-70B |
|---|---|---|
| GPQA Diamond | 69.4% | 26.3% |
| LMArena Expert | 1321 | 1039 |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |
Multimodal Not comparable
GPT-5 Nano: 31.3 (#108), Llama 2-70B: —
| Benchmark | GPT-5 Nano | Llama 2-70B |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual GPT-5 Nano leads
GPT-5 Nano: 45.3 (#172), Llama 2-70B: 27.7 (#274)
| Benchmark | GPT-5 Nano | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1313 | 1045 |
| LMArena Chinese | 1356 | 995 |
| LMArena German | 1327 | 1041 |
| LMArena Japanese | 1226 | 927 |
| LMArena Korean | 1269 | 964 |
| LMArena Russian | 1296 | 1083 |
| LMArena Spanish | 1360 | 1143 |
| LMArena French | — | 1090 |
Instruction Following GPT-5 Nano leads
GPT-5 Nano: 75.0 (#79), Llama 2-70B: 54.9 (#278)
| Benchmark | GPT-5 Nano | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1306 | 1071 |
| IFEval | 93.2% | — |
Long Context Too close to call
GPT-5 Nano: 31.3 (#281), Llama 2-70B: 32.3 (#270)
| Benchmark | GPT-5 Nano | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1312 | 1062 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference GPT-5 Nano leads
GPT-5 Nano: 39.1 (#249), Llama 2-70B: 32.3 (#279)
| Benchmark | GPT-5 Nano | Llama 2-70B |
|---|---|---|
| LMArena Text | 1320 | 1115 |
| LMArena Creative Writing | 1249 | 1075 |
| LMArena Multi-Turn | 1311 | 1088 |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
Frequently asked questions
Is GPT-5 Nano better than Llama 2-70B?
GPT-5 Nano is the stronger model overall, scoring 33.5 to 24.4 on the Noometry Index.
Is GPT-5 Nano or Llama 2-70B better for coding?
GPT-5 Nano scores higher on coding benchmarks: 33.6 versus 31.4 in the Noometry coding category.
How many benchmarks do GPT-5 Nano and Llama 2-70B share?
22 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Llama 2-70B has 35.