Model comparison
Claude 2.1 vs GPT-4 Turbo
GPT-4 Turbo is the stronger model overall, scoring 30.3 to 24.9 on the Noometry Index.
Last verified . 7 shared benchmarks.
Summary
- They share 7 benchmarks with published results for both. Claude 2.1 scores higher in 2 categories and GPT-4 Turbo in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-4 Turbo leads 24.3 to 15.5.
- The biggest single-benchmark swing is GPQA Diamond: 33% for Claude 2.1 and 46.6% for GPT-4 Turbo.
Side by side
| Claude 2.1 | GPT-4 Turbo | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 24.9 | 30.3 |
| Released | 2023-11-21 | 2023-11-06 |
| Weights | Proprietary | Proprietary |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $10 |
| Output $ / M tokens | — | $30 |
| Results tracked | 7 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4 Turbo leads
Claude 2.1: 25.8 (#322), GPT-4 Turbo: 33.4 (#247)
| Benchmark | Claude 2.1 | GPT-4 Turbo |
|---|---|---|
| WeirdML | 7.1% | 18% |
| BigCodeBench Instruct | — | 48.2% |
| LMArena Coding | — | 1268 |
| BigCodeBench Complete | — | 58.2% |
| HumanEval+ | — | 86.6% |
| MBPP+ | — | 73.3% |
Agentic & Tool Use Not comparable
Claude 2.1: —, GPT-4 Turbo: —
| Benchmark | Claude 2.1 | GPT-4 Turbo |
|---|---|---|
| METR Time Horizons | — | 36.7% |
Reasoning Claude 2.1 leads
Claude 2.1: 20.6 (#216), GPT-4 Turbo: 14.9 (#311)
| Benchmark | Claude 2.1 | GPT-4 Turbo |
|---|---|---|
| DTBench | 51% | 61.6% |
| Epoch Capabilities Index | 119.22 | 127.25 |
| ForecastBench | 54.2 | 59.4 |
| SimpleBench | — | 25.1% |
| Chess Puzzles | — | 6% |
| LMArena Hard Prompts | — | 1251 |
| LMCA | — | 9.8% |
Math Too close to call
Claude 2.1: 9.6 (#309), GPT-4 Turbo: 8.6 (#316)
| Benchmark | Claude 2.1 | GPT-4 Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | 6.7% |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| LMArena Math | — | 1272 |
| MATH Level 5 | — | 46.7% |
Knowledge GPT-4 Turbo leads
Claude 2.1: 15.5 (#287), GPT-4 Turbo: 24.3 (#263)
| Benchmark | Claude 2.1 | GPT-4 Turbo |
|---|---|---|
| GPQA Diamond | 33% | 46.6% |
| MMLU | 73.5% | 81.3% |
| Confabulations | — | 28.4% |
| LMArena Expert | — | 1223 |
Multimodal Not comparable
Claude 2.1: —, GPT-4 Turbo: 30.0 (#104)
| Benchmark | Claude 2.1 | GPT-4 Turbo |
|---|---|---|
| LMArena Vision | — | 1090 |
Multilingual Not comparable
Claude 2.1: —, GPT-4 Turbo: 40.7 (#211)
| Benchmark | Claude 2.1 | GPT-4 Turbo |
|---|---|---|
| LMArena Non-English | — | 1245 |
| LMArena Chinese | — | 1242 |
| LMArena French | — | 1275 |
| LMArena German | — | 1259 |
| LMArena Japanese | — | 1194 |
| LMArena Korean | — | 1187 |
| LMArena Russian | — | 1259 |
| LMArena Spanish | — | 1260 |
Instruction Following Not comparable
Claude 2.1: —, GPT-4 Turbo: 66.0 (#211)
| Benchmark | Claude 2.1 | GPT-4 Turbo |
|---|---|---|
| LMArena Instruction Following | — | 1250 |
Long Context Not comparable
Claude 2.1: —, GPT-4 Turbo: 38.0 (#200)
| Benchmark | Claude 2.1 | GPT-4 Turbo |
|---|---|---|
| LMArena Longer Query | — | 1254 |
Writing & Preference Not comparable
Claude 2.1: —, GPT-4 Turbo: 47.9 (#201)
| Benchmark | Claude 2.1 | GPT-4 Turbo |
|---|---|---|
| LMArena Text | — | 1272 |
| LMArena Creative Writing | — | 1269 |
| LMArena Multi-Turn | — | 1267 |
Frequently asked questions
Is Claude 2.1 better than GPT-4 Turbo?
GPT-4 Turbo is the stronger model overall, scoring 30.3 to 24.9 on the Noometry Index.
Is Claude 2.1 or GPT-4 Turbo better for coding?
GPT-4 Turbo scores higher on coding benchmarks: 33.4 versus 25.8 in the Noometry coding category.
How many benchmarks do Claude 2.1 and GPT-4 Turbo share?
7 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and GPT-4 Turbo has 36.