Model comparison
GPT-5 Nano vs Llama 2-13B
GPT-5 Nano is the stronger model overall, scoring 33.4 to 29.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
MetaSummary
- They share 18 benchmarks with published results for both. GPT-5 Nano scores higher in 7 categories and Llama 2-13B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where GPT-5 Nano leads 75.2 to 53.5.
- The biggest single-benchmark swing is Chess Puzzles: 27% for GPT-5 Nano and 0% for Llama 2-13B.
- Llama 2-13B has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Nano | Llama 2-13B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 33.4 | 29.1 |
| 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 | 48 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Nano leads
GPT-5 Nano: 33.3 (#248), Llama 2-13B: 30.4 (#287)
| Benchmark | GPT-5 Nano | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1351 | 1062 |
| SWE-bench Verified (bash only) | 34.8% | — |
| WeirdML | 38.1% | — |
| ALE-Bench | 718.67 | — |
Agentic & Tool Use Not comparable
GPT-5 Nano: 25.6 (#99), Llama 2-13B: —
| Benchmark | GPT-5 Nano | Llama 2-13B |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
Reasoning GPT-5 Nano leads
GPT-5 Nano: 16.4 (#291), Llama 2-13B: 12.3 (#333)
| Benchmark | GPT-5 Nano | Llama 2-13B |
|---|---|---|
| Chess Puzzles | 27% | 0% |
| LMArena Hard Prompts | 1329 | 1051 |
| DTBench | 62.7% | 42.2% |
| Epoch Capabilities Index | 139.39 | 105.8 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| Mystery Game Puzzles | 9% | — |
| LMCA | 7.9% | — |
| BIG-Bench Hard | — | 58.2% |
| ForecastBench | 59.1 | — |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math Too close to call
GPT-5 Nano: 29.1 (#221), Llama 2-13B: 28.7 (#226)
| Benchmark | GPT-5 Nano | Llama 2-13B |
|---|---|---|
| LMArena Math | 1318 | 1065 |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 81.1% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
| GSM8K | — | 36.9% |
Knowledge GPT-5 Nano leads
GPT-5 Nano: 35.8 (#166), Llama 2-13B: 27.5 (#244)
| Benchmark | GPT-5 Nano | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1321 | 1030 |
| GPQA Diamond | 69.4% | — |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
GPT-5 Nano: 30.7 (#102), Llama 2-13B: —
| Benchmark | GPT-5 Nano | Llama 2-13B |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
| ScienceQA | — | 55.8% |
Multilingual GPT-5 Nano leads
GPT-5 Nano: 45.5 (#167), Llama 2-13B: 26.7 (#274)
| Benchmark | GPT-5 Nano | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1313 | 1024 |
| LMArena Chinese | 1355 | 1001 |
| LMArena German | 1329 | 1009 |
| LMArena Korean | 1269 | 953 |
| LMArena Russian | 1296 | 1055 |
| LMArena Spanish | 1360 | 1086 |
| LMArena French | — | 1043 |
| LMArena Japanese | — | 894 |
Instruction Following GPT-5 Nano leads
GPT-5 Nano: 75.2 (#72), Llama 2-13B: 53.5 (#282)
| Benchmark | GPT-5 Nano | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1306 | 1046 |
| IFEval | 93.2% | — |
Long Context Llama 2-13B leads
GPT-5 Nano: 31.3 (#275), Llama 2-13B: 32.3 (#264)
| Benchmark | GPT-5 Nano | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1313 | 1064 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference GPT-5 Nano leads
GPT-5 Nano: 39.4 (#244), Llama 2-13B: 30.0 (#284)
| Benchmark | GPT-5 Nano | Llama 2-13B |
|---|---|---|
| LMArena Text | 1320 | 1085 |
| LMArena Creative Writing | 1250 | 1047 |
| LMArena Multi-Turn | 1311 | 1050 |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
Frequently asked questions
Is GPT-5 Nano better than Llama 2-13B?
GPT-5 Nano is the stronger model overall, scoring 33.4 to 29.1 on the Noometry Index.
Is GPT-5 Nano or Llama 2-13B better for coding?
GPT-5 Nano scores higher on coding benchmarks: 33.3 versus 30.4 in the Noometry coding category.
How many benchmarks do GPT-5 Nano and Llama 2-13B share?
18 benchmarks have published results for both models. GPT-5 Nano has 48 scored results on Noometry and Llama 2-13B has 32.