Model comparison
GPT-4.1 mini vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.5 to 33.5 on the Noometry Index. GPT-4.1 mini costs 2.4× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
Summary
- They share 32 benchmarks with published results for both. GPT-4.1 mini 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 56.8 to 23.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 44.7% for GPT-4.1 mini and 96.1% for Kimi K2.6.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
- GPT-4.1 mini 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 mini | Kimi K2.6 | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 33.5 | 47.5 |
| Released | 2025-04-14 | 2026-04-20 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 33K | 262K |
| Input $ / M tokens | $0.40 | $0.95 |
| Output $ / M tokens | $1.60 | $4 |
| Results tracked | 47 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
GPT-4.1 mini: 30.4 (#286), Kimi K2.6: 50.5 (#41)
| Benchmark | GPT-4.1 mini | Kimi K2.6 |
|---|---|---|
| SciCode | 40.4% | 53.5% |
| WeirdML | 37.6% | 55.9% |
| LMArena Coding | 1367 | 1488 |
| SWE-bench Verified | — | 76.7% |
| SWE-bench Verified (bash only) | 23.9% | — |
| Aider Polyglot | 32.4% | — |
| LMArena WebDev | — | 1509 |
| BigCodeBench Instruct | 48.9% | — |
| CadEval | 16% | — |
| ALE-Bench | — | 1,093 |
Agentic & Tool Use GPT-4.1 mini leads
GPT-4.1 mini: 33.0 (#52), Kimi K2.6: 21.8 (#128)
| Benchmark | GPT-4.1 mini | Kimi K2.6 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | — |
| 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 mini: 10.9 (#335), Kimi K2.6: 39.6 (#51)
| Benchmark | GPT-4.1 mini | Kimi K2.6 |
|---|---|---|
| CritPt | 0% | 8% |
| Chess Puzzles | 7% | 26% |
| LMArena Hard Prompts | 1349 | 1470 |
| Mystery Game Puzzles | 7% | 18% |
| DTBench | 68.8% | 90.9% |
| LMCA | 21.1% | 37.3% |
| Epoch Capabilities Index | 135.01 | 151.03 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 48.6% | — |
| NYT Connections (extended) | — | 87.2% |
| ARC-AGI-1 | 3.5% | — |
| EBR-Bench | — | 2.4% |
Math Kimi K2.6 leads
GPT-4.1 mini: 23.1 (#264), Kimi K2.6: 56.8 (#34)
| Benchmark | GPT-4.1 mini | Kimi K2.6 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6.7% | 57.2% |
| OTIS Mock AIME 2024-2025 | 44.7% | 96.1% |
| LMArena Math | 1343 | 1475 |
| FrontierMath (Feb 2025 set) | 4.5% | 39% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| ProofBench | — | 16% |
| Omni-MATH | 49.1% | — |
| MATH Level 5 | 87.3% | — |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Kimi K2.6 leads
GPT-4.1 mini: 34.7 (#183), Kimi K2.6: 53.9 (#48)
| Benchmark | GPT-4.1 mini | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 65.8% | 90.8% |
| SimpleQA Verified | 12.7% | 34.9% |
| LMArena Expert | 1338 | 1491 |
| MMLU-Pro | 78.3% | — |
| Vectara Hallucination Rate | — | 10.8% |
| GPQA (HELM) | 61.4% | — |
Multimodal GPT-4.1 mini leads
GPT-4.1 mini: 35.2 (#77), Kimi K2.6: 31.8 (#95)
| Benchmark | GPT-4.1 mini | Kimi K2.6 |
|---|---|---|
| LMArena Vision | 1181 | 1282 |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Kimi K2.6 leads
GPT-4.1 mini: 45.9 (#161), Kimi K2.6: 55.1 (#35)
| Benchmark | GPT-4.1 mini | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1318 | 1446 |
| LMArena Chinese | 1329 | 1521 |
| LMArena French | 1357 | 1471 |
| LMArena German | 1349 | 1449 |
| LMArena Japanese | 1291 | 1442 |
| LMArena Korean | 1298 | 1428 |
| LMArena Russian | 1324 | 1446 |
| LMArena Spanish | 1319 | 1463 |
Instruction Following Kimi K2.6 leads
GPT-4.1 mini: 73.9 (#113), Kimi K2.6: 76.5 (#40)
| Benchmark | GPT-4.1 mini | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1332 | 1451 |
| IFEval | 90.4% | — |
Long Context Kimi K2.6 leads
GPT-4.1 mini: 31.8 (#270), Kimi K2.6: 44.9 (#50)
| Benchmark | GPT-4.1 mini | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1344 | 1468 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Kimi K2.6 leads
GPT-4.1 mini: 48.8 (#193), Kimi K2.6: 68.7 (#25)
| Benchmark | GPT-4.1 mini | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1341 | 1455 |
| LMArena Creative Writing | 1300 | 1434 |
| EQ-Bench Creative Writing | 1147 | 1725 |
| LMArena Multi-Turn | 1354 | 1453 |
| WildBench | 83.8% | — |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is GPT-4.1 mini better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.5 to 33.5 on the Noometry Index. GPT-4.1 mini costs 2.4× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 mini or Kimi K2.6?
GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Kimi K2.6 lists at $0.95 and $4.
Is GPT-4.1 mini or Kimi K2.6 better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.5 versus 30.4 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 mini does, with 1.05M tokens against 262K.
How many benchmarks do GPT-4.1 mini and Kimi K2.6 share?
32 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Kimi K2.6 has 51.