Model comparison
GPT-4.1 vs Llama 2-13B
GPT-4.1 is the stronger model overall, scoring 35.9 to 29.6 on the Noometry Index.
Last verified . 20 shared benchmarks.
MetaSummary
- They share 20 benchmarks with published results for both. GPT-4.1 scores higher in 6 categories and Llama 2-13B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4.1 leads 57.6 to 29.8.
- The biggest single-benchmark swing is DTBench: 68.3% for GPT-4.1 and 42.2% for Llama 2-13B.
- Llama 2-13B has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 | Llama 2-13B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 35.9 | 29.6 |
| Released | 2025-04-14 | 2023-07-18 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 33K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $8 | — |
| Results tracked | 52 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.1 leads
GPT-4.1: 34.4 (#238), Llama 2-13B: 30.9 (#291)
| Benchmark | GPT-4.1 | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1391 | 1062 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| WeirdML | 39% | — |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |
Agentic & Tool Use Not comparable
GPT-4.1: 34.7 (#43), Llama 2-13B: —
| Benchmark | GPT-4.1 | Llama 2-13B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
Reasoning Llama 2-13B leads
GPT-4.1: 11.7 (#339), Llama 2-13B: 12.8 (#337)
| Benchmark | GPT-4.1 | Llama 2-13B |
|---|---|---|
| Chess Puzzles | 6% | 0% |
| LMArena Hard Prompts | 1384 | 1051 |
| DTBench | 68.3% | 42.2% |
| Epoch Capabilities Index | 136.78 | 106.17 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| Kagi LLM Benchmark | 52.3% | — |
| ARC-AGI-1 | 5.5% | — |
| EnigmaEval | 2.2% | — |
| LMCA | 25.6% | — |
| BIG-Bench Hard | — | 58.2% |
| ForecastBench | 61.5 | — |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math Llama 2-13B leads
GPT-4.1: 22.3 (#280), Llama 2-13B: 31.1 (#229)
| Benchmark | GPT-4.1 | Llama 2-13B |
|---|---|---|
| LMArena Math | 1370 | 1065 |
| FrontierMath (Tiers 1-3) | 6% | — |
| OTIS Mock AIME 2024-2025 | 38.3% | — |
| Omni-MATH | 47.1% | — |
| MATH Level 5 | 83% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
| GSM8K | — | 36.9% |
Knowledge GPT-4.1 leads
GPT-4.1: 37.1 (#160), Llama 2-13B: 28.1 (#249)
| Benchmark | GPT-4.1 | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1364 | 1030 |
| GPQA Diamond | 66.9% | — |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| Vectara Hallucination Rate | 5.6% | — |
| GPQA (HELM) | 65.9% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
GPT-4.1: 38.2 (#67), Llama 2-13B: —
| Benchmark | GPT-4.1 | Llama 2-13B |
|---|---|---|
| LMArena Vision | 1211 | — |
| GeoBench | 72% | — |
| ScienceQA | — | 55.8% |
Multilingual GPT-4.1 leads
GPT-4.1: 49.4 (#133), Llama 2-13B: 26.5 (#279)
| Benchmark | GPT-4.1 | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1370 | 1024 |
| LMArena Chinese | 1382 | 1001 |
| LMArena French | 1382 | 1044 |
| LMArena German | 1381 | 1009 |
| LMArena Japanese | 1319 | 894 |
| LMArena Korean | 1339 | 953 |
| LMArena Russian | 1377 | 1055 |
| LMArena Spanish | 1376 | 1087 |
Instruction Following GPT-4.1 leads
GPT-4.1: 71.3 (#153), Llama 2-13B: 53.3 (#287)
| Benchmark | GPT-4.1 | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1367 | 1045 |
| IFEval | 83.8% | — |
Long Context GPT-4.1 leads
GPT-4.1: 40.0 (#163), Llama 2-13B: 32.3 (#269)
| Benchmark | GPT-4.1 | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1385 | 1064 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference GPT-4.1 leads
GPT-4.1: 57.6 (#125), Llama 2-13B: 29.8 (#289)
| Benchmark | GPT-4.1 | Llama 2-13B |
|---|---|---|
| LMArena Text | 1383 | 1084 |
| LMArena Creative Writing | 1363 | 1047 |
| LMArena Multi-Turn | 1398 | 1050 |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is GPT-4.1 better than Llama 2-13B?
GPT-4.1 is the stronger model overall, scoring 35.9 to 29.6 on the Noometry Index.
Is GPT-4.1 or Llama 2-13B better for coding?
GPT-4.1 scores higher on coding benchmarks: 34.4 versus 30.9 in the Noometry coding category.
How many benchmarks do GPT-4.1 and Llama 2-13B share?
20 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Llama 2-13B has 32.