Model comparison
Claude 2 vs GPT-4.1 mini
GPT-4.1 mini is the stronger model overall, scoring 33.6 to 25.0 on the Noometry Index.
Last verified . 5 shared benchmarks.
Summary
- They share 5 benchmarks with published results for both. Claude 2 scores higher in 1 category and GPT-4.1 mini in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-4.1 mini leads 34.7 to 16.9.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for Claude 2 and 87.3% for GPT-4.1 mini.
Side by side
| Claude 2 | GPT-4.1 mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 25.0 | 33.6 |
| Released | 2023-07-11 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $1.60 |
| Results tracked | 8 | 47 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude 2: —, GPT-4.1 mini: 30.6 (#293)
| Benchmark | Claude 2 | GPT-4.1 mini |
|---|---|---|
| SWE-bench Verified (bash only) | — | 23.9% |
| Aider Polyglot | — | 32.4% |
| SciCode | — | 40.4% |
| WeirdML | — | 37.6% |
| BigCodeBench Instruct | — | 48.9% |
| LMArena Coding | — | 1367 |
| CadEval | — | 16% |
| HumanEval+ | 61.6% | — |
Agentic & Tool Use Not comparable
Claude 2: —, GPT-4.1 mini: 33.3 (#55)
| Benchmark | Claude 2 | GPT-4.1 mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 50.5% |
Reasoning Claude 2 leads
Claude 2: 21.7 (#216), GPT-4.1 mini: 10.8 (#340)
| Benchmark | Claude 2 | GPT-4.1 mini |
|---|---|---|
| DTBench | 51.9% | 68.8% |
| Epoch Capabilities Index | 120.13 | 135.01 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 48.6% |
| ARC-AGI-1 | — | 3.5% |
| CritPt | — | 0% |
| Chess Puzzles | — | 7% |
| LMArena Hard Prompts | — | 1349 |
| Mystery Game Puzzles | — | 7% |
| LMCA | — | 21.1% |
Math GPT-4.1 mini leads
Claude 2: 9.3 (#320), GPT-4.1 mini: 24.1 (#270)
| Benchmark | Claude 2 | GPT-4.1 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 44.7% |
| MATH Level 5 | 11.7% | 87.3% |
| FrontierMath (Tiers 1-3) | — | 6.7% |
| Omni-MATH | — | 49.1% |
| LMArena Math | — | 1343 |
| FrontierMath (Feb 2025 set) | — | 4.5% |
Knowledge GPT-4.1 mini leads
Claude 2: 16.9 (#287), GPT-4.1 mini: 34.7 (#194)
| Benchmark | Claude 2 | GPT-4.1 mini |
|---|---|---|
| GPQA Diamond | 34.7% | 65.8% |
| SimpleQA Verified | — | 12.7% |
| MMLU-Pro | — | 78.3% |
| GPQA (HELM) | — | 61.4% |
| LMArena Expert | — | 1338 |
| MMLU | 78.5% | — |
| TriviaQA | 87.5% | — |
Multimodal Not comparable
Claude 2: —, GPT-4.1 mini: 35.8 (#82)
| Benchmark | Claude 2 | GPT-4.1 mini |
|---|---|---|
| LMArena Vision | — | 1181 |
Multilingual Not comparable
Claude 2: —, GPT-4.1 mini: 45.7 (#166)
| Benchmark | Claude 2 | GPT-4.1 mini |
|---|---|---|
| LMArena Non-English | — | 1318 |
| LMArena Chinese | — | 1329 |
| LMArena French | — | 1358 |
| LMArena German | — | 1351 |
| LMArena Japanese | — | 1290 |
| LMArena Korean | — | 1298 |
| LMArena Russian | — | 1324 |
| LMArena Spanish | — | 1319 |
Instruction Following Not comparable
Claude 2: —, GPT-4.1 mini: 73.7 (#118)
| Benchmark | Claude 2 | GPT-4.1 mini |
|---|---|---|
| IFEval | — | 90.4% |
| LMArena Instruction Following | — | 1333 |
Long Context Not comparable
Claude 2: —, GPT-4.1 mini: 31.8 (#275)
| Benchmark | Claude 2 | GPT-4.1 mini |
|---|---|---|
| Fiction.LiveBench | — | 44.4% |
| LMArena Longer Query | — | 1344 |
Writing & Preference Not comparable
Claude 2: —, GPT-4.1 mini: 48.6 (#199)
| Benchmark | Claude 2 | GPT-4.1 mini |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1300 |
| EQ-Bench Creative Writing | — | 1147 |
| WildBench | — | 83.8% |
| LMArena Multi-Turn | — | 1354 |
Frequently asked questions
Is Claude 2 better than GPT-4.1 mini?
GPT-4.1 mini is the stronger model overall, scoring 33.6 to 25.0 on the Noometry Index.
How many benchmarks do Claude 2 and GPT-4.1 mini share?
5 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and GPT-4.1 mini has 47.