Model comparison
GPT-4.1 vs Kimi K2 Thinking Turbo
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 35.9 on the Noometry Index.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. GPT-4.1 scores higher in 0 categories and Kimi K2 Thinking Turbo in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 Thinking Turbo leads 47.4 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 38.3% for GPT-4.1 and 83.1% for Kimi K2 Thinking Turbo.
- Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 | Kimi K2 Thinking Turbo | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 35.9 | 45.8 |
| Released | 2025-04-14 | 2025-11-06 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 33K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $8 | — |
| Results tracked | 52 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 Thinking Turbo leads
GPT-4.1: 34.4 (#238), Kimi K2 Thinking Turbo: 38.4 (#178)
| Benchmark | GPT-4.1 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Coding | 1391 | 1454 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| LMArena WebDev | — | 1322 |
| WeirdML | 39% | — |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |
Agentic & Tool Use Not comparable
GPT-4.1: 34.7 (#43), Kimi K2 Thinking Turbo: —
| Benchmark | GPT-4.1 | Kimi K2 Thinking Turbo |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
Reasoning Kimi K2 Thinking Turbo leads
GPT-4.1: 11.7 (#339), Kimi K2 Thinking Turbo: 32.5 (#75)
| Benchmark | GPT-4.1 | Kimi K2 Thinking Turbo |
|---|---|---|
| Chess Puzzles | 6% | 20% |
| LMArena Hard Prompts | 1384 | 1428 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| Kagi LLM Benchmark | 52.3% | — |
| ARC-AGI-1 | 5.5% | — |
| EnigmaEval | 2.2% | — |
| DTBench | 68.3% | — |
| LMCA | 25.6% | — |
| Epoch Capabilities Index | 136.78 | — |
| ForecastBench | 61.5 | — |
Math Kimi K2 Thinking Turbo leads
GPT-4.1: 22.3 (#280), Kimi K2 Thinking Turbo: 47.4 (#68)
| Benchmark | GPT-4.1 | Kimi K2 Thinking Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 38.3% | 83.1% |
| LMArena Math | 1370 | 1429 |
| FrontierMath (Tiers 1-3) | 6% | — |
| Omni-MATH | 47.1% | — |
| MATH Level 5 | 83% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Kimi K2 Thinking Turbo leads
GPT-4.1: 37.1 (#160), Kimi K2 Thinking Turbo: 50.9 (#69)
| Benchmark | GPT-4.1 | Kimi K2 Thinking Turbo |
|---|---|---|
| GPQA Diamond | 66.9% | 84.2% |
| LMArena Expert | 1364 | 1439 |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| Vectara Hallucination Rate | 5.6% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal Not comparable
GPT-4.1: 38.2 (#67), Kimi K2 Thinking Turbo: —
| Benchmark | GPT-4.1 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Vision | 1211 | — |
| GeoBench | 72% | — |
Multilingual Kimi K2 Thinking Turbo leads
GPT-4.1: 49.4 (#133), Kimi K2 Thinking Turbo: 51.4 (#109)
| Benchmark | GPT-4.1 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Non-English | 1370 | 1398 |
| LMArena Chinese | 1382 | 1456 |
| LMArena French | 1382 | 1425 |
| LMArena German | 1381 | 1390 |
| LMArena Japanese | 1319 | 1357 |
| LMArena Korean | 1339 | 1330 |
| LMArena Russian | 1377 | 1391 |
| LMArena Spanish | 1376 | 1406 |
Instruction Following Kimi K2 Thinking Turbo leads
GPT-4.1: 71.3 (#153), Kimi K2 Thinking Turbo: 74.0 (#109)
| Benchmark | GPT-4.1 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Instruction Following | 1367 | 1403 |
| IFEval | 83.8% | — |
Long Context Kimi K2 Thinking Turbo leads
GPT-4.1: 40.0 (#163), Kimi K2 Thinking Turbo: 43.2 (#102)
| Benchmark | GPT-4.1 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Longer Query | 1385 | 1415 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference Kimi K2 Thinking Turbo leads
GPT-4.1: 57.6 (#125), Kimi K2 Thinking Turbo: 60.0 (#104)
| Benchmark | GPT-4.1 | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Text | 1383 | 1415 |
| LMArena Creative Writing | 1363 | 1374 |
| LMArena Multi-Turn | 1398 | 1414 |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is GPT-4.1 better than Kimi K2 Thinking Turbo?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 35.9 on the Noometry Index.
Is GPT-4.1 or Kimi K2 Thinking Turbo better for coding?
Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.4 versus 34.4 in the Noometry coding category.
How many benchmarks do GPT-4.1 and Kimi K2 Thinking Turbo share?
20 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Kimi K2 Thinking Turbo has 21.