Model comparison
Claude 2.1 vs GPT-5-Codex
GPT-5-Codex is the stronger model overall, scoring 37.9 to 25.2 on the Noometry Index.
Last verified . 1 shared benchmarks.
Summary
- They share 1 benchmark with published results for both. Claude 2.1 scores higher in 0 categories and GPT-5-Codex in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-5-Codex leads 42.4 to 26.2.
- The biggest single-benchmark swing is WeirdML: 7.1% for Claude 2.1 and 54.5% for GPT-5-Codex.
Side by side
| Claude 2.1 | GPT-5-Codex | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 25.2 | 37.9 |
| Released | 2023-11-21 | 2025-09-15 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $10 |
| Results tracked | 7 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5-Codex leads
Claude 2.1: 26.2 (#327), GPT-5-Codex: 42.4 (#103)
| Benchmark | Claude 2.1 | GPT-5-Codex |
|---|---|---|
| WeirdML | 7.1% | 54.5% |
Agentic & Tool Use Not comparable
Claude 2.1: —, GPT-5-Codex: 31.0 (#72)
| Benchmark | Claude 2.1 | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | — | 44.3% |
Reasoning GPT-5-Codex leads
Claude 2.1: 21.4 (#221), GPT-5-Codex: 30.9 (#83)
| Benchmark | Claude 2.1 | GPT-5-Codex |
|---|---|---|
| Kagi LLM Benchmark | — | 70.3% |
| DTBench | 51% | — |
| Epoch Capabilities Index | 119.27 | — |
| ForecastBench | 54.2 | — |
Math Not comparable
Claude 2.1: 10.2 (#315), GPT-5-Codex: —
| Benchmark | Claude 2.1 | GPT-5-Codex |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | — |
Knowledge Not comparable
Claude 2.1: 15.4 (#292), GPT-5-Codex: —
| Benchmark | Claude 2.1 | GPT-5-Codex |
|---|---|---|
| GPQA Diamond | 33% | — |
| MMLU | 73.5% | — |
Frequently asked questions
Is Claude 2.1 better than GPT-5-Codex?
GPT-5-Codex is the stronger model overall, scoring 37.9 to 25.2 on the Noometry Index.
Is Claude 2.1 or GPT-5-Codex better for coding?
GPT-5-Codex scores higher on coding benchmarks: 42.4 versus 26.2 in the Noometry coding category.
How many benchmarks do Claude 2.1 and GPT-5-Codex share?
1 benchmark has published results for both models. Claude 2.1 has 7 scored results on Noometry and GPT-5-Codex has 3.