Model comparison
GPT-4.1 vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.7 to 35.9 on the Noometry Index.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. GPT-4.1 scores higher in 2 categories and Kimi K2.6 in 8 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.6 leads 57.0 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 38.3% for GPT-4.1 and 96.1% for Kimi K2.6.
- Kimi K2.6 is cheaper at $0.95 / $4 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 262K.
- Kimi K2.6 has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 | Kimi K2.6 | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 35.9 | 47.7 |
| Released | 2025-04-14 | 2026-04-20 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 33K | 262K |
| Input $ / M tokens | $2 | $0.95 |
| Output $ / M tokens | $8 | $4 |
| Results tracked | 52 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
GPT-4.1: 34.4 (#238), Kimi K2.6: 50.7 (#43)
| Benchmark | GPT-4.1 | Kimi K2.6 |
|---|---|---|
| SWE-bench Verified | 48.5% | 76.7% |
| WeirdML | 39% | 55.9% |
| LMArena Coding | 1391 | 1488 |
| ALE-Bench | 558.1 | 1,093 |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| LMArena WebDev | — | 1509 |
| SciCode | — | 53.5% |
| CadEval | 42% | — |
Agentic & Tool Use GPT-4.1 leads
GPT-4.1: 34.7 (#43), Kimi K2.6: 21.9 (#137)
| Benchmark | GPT-4.1 | Kimi K2.6 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
| OSWorld 2.0 | — | 4.6% |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| Vending-Bench 2 | — | 6,205 |
Reasoning Kimi K2.6 leads
GPT-4.1: 11.7 (#339), Kimi K2.6: 40.5 (#55)
| Benchmark | GPT-4.1 | Kimi K2.6 |
|---|---|---|
| Chess Puzzles | 6% | 26% |
| LMArena Hard Prompts | 1384 | 1470 |
| DTBench | 68.3% | 90.9% |
| LMCA | 25.6% | 37.3% |
| Epoch Capabilities Index | 136.78 | 151.05 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| Kagi LLM Benchmark | 52.3% | — |
| NYT Connections (extended) | — | 87.2% |
| ARC-AGI-1 | 5.5% | — |
| CritPt | — | 8% |
| EnigmaEval | 2.2% | — |
| EBR-Bench | — | 2.4% |
| Mystery Game Puzzles | — | 18% |
| ForecastBench | 61.5 | — |
Math Kimi K2.6 leads
GPT-4.1: 22.3 (#280), Kimi K2.6: 57.0 (#41)
| Benchmark | GPT-4.1 | Kimi K2.6 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6% | 57.2% |
| OTIS Mock AIME 2024-2025 | 38.3% | 96.1% |
| LMArena Math | 1370 | 1475 |
| FrontierMath (Feb 2025 set) | 5.5% | 39% |
| FrontierMath Tier 4 (v1) | 0% | 14.6% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| ProofBench | — | 16% |
| Omni-MATH | 47.1% | — |
| MATH Level 5 | 83% | — |
Knowledge Kimi K2.6 leads
GPT-4.1: 37.1 (#160), Kimi K2.6: 54.0 (#54)
| Benchmark | GPT-4.1 | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 66.9% | 90.8% |
| SimpleQA Verified | 31.1% | 34.9% |
| Vectara Hallucination Rate | 5.6% | 10.8% |
| LMArena Expert | 1364 | 1491 |
| Humanity's Last Exam | 5.4% | — |
| MMLU-Pro | 81.1% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal GPT-4.1 leads
GPT-4.1: 38.2 (#67), Kimi K2.6: 31.6 (#103)
| Benchmark | GPT-4.1 | Kimi K2.6 |
|---|---|---|
| LMArena Vision | 1211 | 1283 |
| GeoBench | 72% | — |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Kimi K2.6 leads
GPT-4.1: 49.4 (#133), Kimi K2.6: 54.9 (#37)
| Benchmark | GPT-4.1 | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1370 | 1446 |
| LMArena Chinese | 1382 | 1521 |
| LMArena French | 1382 | 1471 |
| LMArena German | 1381 | 1450 |
| LMArena Japanese | 1319 | 1443 |
| LMArena Korean | 1339 | 1427 |
| LMArena Russian | 1377 | 1446 |
| LMArena Spanish | 1376 | 1464 |
Instruction Following Kimi K2.6 leads
GPT-4.1: 71.3 (#153), Kimi K2.6: 76.3 (#43)
| Benchmark | GPT-4.1 | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1367 | 1451 |
| IFEval | 83.8% | — |
Long Context Kimi K2.6 leads
GPT-4.1: 40.0 (#163), Kimi K2.6: 44.9 (#52)
| Benchmark | GPT-4.1 | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1385 | 1468 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference Kimi K2.6 leads
GPT-4.1: 57.6 (#125), Kimi K2.6: 68.5 (#26)
| Benchmark | GPT-4.1 | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1383 | 1455 |
| LMArena Creative Writing | 1363 | 1434 |
| EQ-Bench Creative Writing | 1420 | 1725 |
| LMArena Multi-Turn | 1398 | 1453 |
| WildBench | 85.4% | — |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is GPT-4.1 better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 35.9 on the Noometry Index.
Which is cheaper, GPT-4.1 or Kimi K2.6?
Kimi K2.6 is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; GPT-4.1 lists at $2 and $8.
Is GPT-4.1 or Kimi K2.6 better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 262K.
How many benchmarks do GPT-4.1 and Kimi K2.6 share?
33 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Kimi K2.6 has 51.