Model comparison
GPT-5 Mini vs Llama 2-13B
GPT-5 Mini is the stronger model overall, scoring 41.8 to 29.6 on the Noometry Index.
Last verified . 20 shared benchmarks.
MetaSummary
- They share 20 benchmarks with published results for both. GPT-5 Mini scores higher in 8 categories and Llama 2-13B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-5 Mini leads 55.2 to 29.8.
- The biggest single-benchmark swing is DTBench: 80.5% for GPT-5 Mini and 42.2% for Llama 2-13B.
- Llama 2-13B has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Mini | Llama 2-13B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 41.8 | 29.6 |
| Released | 2025-08-07 | 2023-07-18 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $2 | — |
| Results tracked | 60 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Mini leads
GPT-5 Mini: 40.1 (#146), Llama 2-13B: 30.9 (#291)
| Benchmark | GPT-5 Mini | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1406 | 1062 |
| SWE-bench Verified | 64.7% | — |
| SWE-bench Verified (bash only) | 59.8% | — |
| SWE-bench Multilingual | 39.7% | — |
| SciCode | 39.2% | — |
| WeirdML | 52.7% | — |
| ALE-Bench | 799.77 | — |
| AlgoTune | 1.38 | — |
Agentic & Tool Use Not comparable
GPT-5 Mini: 31.1 (#70), Llama 2-13B: —
| Benchmark | GPT-5 Mini | Llama 2-13B |
|---|---|---|
| Terminal-Bench | 34.8% | — |
| Berkeley Function Calling Leaderboard | 55.5% | — |
| Vending-Bench 2 | -31.18 | — |
Reasoning GPT-5 Mini leads
GPT-5 Mini: 23.9 (#168), Llama 2-13B: 12.8 (#337)
| Benchmark | GPT-5 Mini | Llama 2-13B |
|---|---|---|
| Chess Puzzles | 30% | 0% |
| LMArena Hard Prompts | 1380 | 1051 |
| DTBench | 80.5% | 42.2% |
| Epoch Capabilities Index | 145.52 | 106.17 |
| ARC-AGI-2 | 4.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| ARC-AGI-1 | 54.3% | — |
| CritPt | 0% | — |
| EnigmaEval | 8.2% | — |
| Mystery Game Puzzles | 10% | — |
| LMCA | 34.2% | — |
| BIG-Bench Hard | — | 58.2% |
| ForecastBench | 61 | — |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math GPT-5 Mini leads
GPT-5 Mini: 46.7 (#69), Llama 2-13B: 31.1 (#229)
| Benchmark | GPT-5 Mini | Llama 2-13B |
|---|---|---|
| LMArena Math | 1378 | 1065 |
| FrontierMath (Tiers 1-3) | 46.7% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 9% | — |
| Omni-MATH | 72.2% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 27.2% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
| GSM8K | — | 36.9% |
Knowledge GPT-5 Mini leads
GPT-5 Mini: 45.6 (#86), Llama 2-13B: 28.1 (#249)
| Benchmark | GPT-5 Mini | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1379 | 1030 |
| GPQA Diamond | 75% | — |
| Humanity's Last Exam | 19.4% | — |
| SimpleQA Verified | 21.6% | — |
| MMLU-Pro | 83.5% | — |
| Confabulations | 13.3% | — |
| Vectara Hallucination Rate | 12.9% | — |
| GPQA (HELM) | 75.6% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
GPT-5 Mini: 35.6 (#85), Llama 2-13B: —
| Benchmark | GPT-5 Mini | Llama 2-13B |
|---|---|---|
| LMArena Vision | 1202 | — |
| VPCT | 40.2% | — |
| ScienceQA | — | 55.8% |
Multilingual GPT-5 Mini leads
GPT-5 Mini: 48.9 (#137), Llama 2-13B: 26.5 (#279)
| Benchmark | GPT-5 Mini | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1363 | 1024 |
| LMArena Chinese | 1385 | 1001 |
| LMArena French | 1386 | 1044 |
| LMArena German | 1366 | 1009 |
| LMArena Japanese | 1341 | 894 |
| LMArena Korean | 1308 | 953 |
| LMArena Russian | 1362 | 1055 |
| LMArena Spanish | 1355 | 1087 |
Instruction Following GPT-5 Mini leads
GPT-5 Mini: 76.2 (#46), Llama 2-13B: 53.3 (#287)
| Benchmark | GPT-5 Mini | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1357 | 1045 |
| IFEval | 92.7% | — |
Long Context GPT-5 Mini leads
GPT-5 Mini: 41.9 (#132), Llama 2-13B: 32.3 (#269)
| Benchmark | GPT-5 Mini | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1355 | 1064 |
| Fiction.LiveBench | 69.4% | — |
Writing & Preference GPT-5 Mini leads
GPT-5 Mini: 55.2 (#148), Llama 2-13B: 29.8 (#289)
| Benchmark | GPT-5 Mini | Llama 2-13B |
|---|---|---|
| LMArena Text | 1373 | 1084 |
| LMArena Creative Writing | 1325 | 1047 |
| LMArena Multi-Turn | 1363 | 1050 |
| Short-Story Creative Writing | 83.1% | — |
| EQ-Bench Creative Writing | 1313 | — |
| WildBench | 85.5% | — |
Frequently asked questions
Is GPT-5 Mini better than Llama 2-13B?
GPT-5 Mini is the stronger model overall, scoring 41.8 to 29.6 on the Noometry Index.
Is GPT-5 Mini or Llama 2-13B better for coding?
GPT-5 Mini scores higher on coding benchmarks: 40.1 versus 30.9 in the Noometry coding category.
How many benchmarks do GPT-5 Mini and Llama 2-13B share?
20 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and Llama 2-13B has 32.