Model comparison
GPT-5.4 Pro vs Llama 2-70B
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 24.4 on the Noometry Index.
Last verified . 2 shared benchmarks.
MetaSummary
- They share 2 benchmarks with published results for both. GPT-5.4 Pro scores higher in 4 categories and Llama 2-70B in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 Pro leads 72.4 to 8.1.
- The biggest single-benchmark swing is GPQA Diamond: 94.6% for GPT-5.4 Pro and 26.3% for Llama 2-70B.
- Llama 2-70B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 Pro | Llama 2-70B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 58.9 | 24.4 |
| Released | 2026-03-05 | 2023-07-18 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $30 | — |
| Output $ / M tokens | $180 | — |
| Results tracked | 16 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 Pro leads
GPT-5.4 Pro: 43.2 (#90), Llama 2-70B: 31.4 (#286)
| Benchmark | GPT-5.4 Pro | Llama 2-70B |
|---|---|---|
| WeirdML | 57.4% | — |
| LMArena Coding | — | 1079 |
Reasoning GPT-5.4 Pro leads
GPT-5.4 Pro: 70.7 (#13), Llama 2-70B: 14.4 (#325)
| Benchmark | GPT-5.4 Pro | Llama 2-70B |
|---|---|---|
| Epoch Capabilities Index | 158.93 | 113.79 |
| ARC-AGI-2 | 83.3% | — |
| SimpleBench | 74.1% | — |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 30% | — |
| Chess Puzzles | 58.6% | — |
| EnigmaEval | 23.8% | — |
| LMArena Hard Prompts | — | 1073 |
| DTBench | — | 41.6% |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |
Math GPT-5.4 Pro leads
GPT-5.4 Pro: 72.4 (#22), Llama 2-70B: 8.1 (#326)
| Benchmark | GPT-5.4 Pro | Llama 2-70B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | — |
| FrontierMath Tier 4 | 58.5% | — |
| OTIS Mock AIME 2024-2025 | — | 0% |
| LMArena Math | — | 1091 |
| MATH Level 5 | — | 3.3% |
| FrontierMath (Feb 2025 set) | 50% | — |
| FrontierMath Tier 4 (v1) | 37.5% | — |
| GSM8K | — | 69.6% |
Knowledge GPT-5.4 Pro leads
GPT-5.4 Pro: 68.3 (#7), Llama 2-70B: 7.4 (#310)
| Benchmark | GPT-5.4 Pro | Llama 2-70B |
|---|---|---|
| GPQA Diamond | 94.6% | 26.3% |
| Humanity's Last Exam | 44.3% | — |
| SimpleQA Verified | 46.3% | — |
| Vectara Hallucination Rate | 8.3% | — |
| LMArena Expert | — | 1039 |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |
Multilingual Not comparable
GPT-5.4 Pro: —, Llama 2-70B: 27.7 (#274)
| Benchmark | GPT-5.4 Pro | Llama 2-70B |
|---|---|---|
| LMArena Non-English | — | 1045 |
| LMArena Chinese | — | 995 |
| LMArena French | — | 1090 |
| LMArena German | — | 1041 |
| LMArena Japanese | — | 927 |
| LMArena Korean | — | 964 |
| LMArena Russian | — | 1083 |
| LMArena Spanish | — | 1143 |
Instruction Following Not comparable
GPT-5.4 Pro: —, Llama 2-70B: 54.9 (#278)
| Benchmark | GPT-5.4 Pro | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | — | 1071 |
Long Context Not comparable
GPT-5.4 Pro: —, Llama 2-70B: 32.3 (#270)
| Benchmark | GPT-5.4 Pro | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | — | 1062 |
Writing & Preference Not comparable
GPT-5.4 Pro: —, Llama 2-70B: 32.3 (#279)
| Benchmark | GPT-5.4 Pro | Llama 2-70B |
|---|---|---|
| LMArena Text | — | 1115 |
| LMArena Creative Writing | — | 1075 |
| LMArena Multi-Turn | — | 1088 |
Frequently asked questions
Is GPT-5.4 Pro better than Llama 2-70B?
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 24.4 on the Noometry Index.
Is GPT-5.4 Pro or Llama 2-70B better for coding?
GPT-5.4 Pro scores higher on coding benchmarks: 43.2 versus 31.4 in the Noometry coding category.
How many benchmarks do GPT-5.4 Pro and Llama 2-70B share?
2 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and Llama 2-70B has 35.