Model comparison
GPT-4.1 mini vs Kimi K2 (Jul 2025)
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 33.6 on the Noometry Index.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. GPT-4.1 mini scores higher in 2 categories and Kimi K2 (Jul 2025) in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 (Jul 2025) leads 42.7 to 24.1.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 23.9% for GPT-4.1 mini and 63.4% for Kimi K2 (Jul 2025).
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $0.57 / $2.30 for Kimi K2 (Jul 2025).
- GPT-4.1 mini accepts more context: 1.05M tokens versus 262K.
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 mini | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 33.6 | 41.2 |
| Released | 2025-04-14 | 2025-07-12 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 33K | 262K |
| Input $ / M tokens | $0.40 | $0.57 |
| Output $ / M tokens | $1.60 | $2.30 |
| Results tracked | 47 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
GPT-4.1 mini: 30.6 (#293), Kimi K2 (Jul 2025): 42.4 (#102)
| Benchmark | GPT-4.1 mini | Kimi K2 (Jul 2025) |
|---|---|---|
| SWE-bench Verified (bash only) | 23.9% | 63.4% |
| Aider Polyglot | 32.4% | 59.1% |
| WeirdML | 37.6% | 42.8% |
| LMArena Coding | 1367 | 1399 |
| SciCode | 40.4% | — |
| GSO | — | 4.9% |
| BigCodeBench Instruct | 48.9% | — |
| CadEval | 16% | — |
| ALE-Bench | — | 597.5 |
Agentic & Tool Use Too close to call
GPT-4.1 mini: 33.3 (#55), Kimi K2 (Jul 2025): 32.4 (#64)
| Benchmark | GPT-4.1 mini | Kimi K2 (Jul 2025) |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | 59.1% |
| Terminal-Bench | — | 35.7% |
| METR Time Horizons | — | 59.2% |
Reasoning Kimi K2 (Jul 2025) leads
GPT-4.1 mini: 10.8 (#340), Kimi K2 (Jul 2025): 23.3 (#179)
| Benchmark | GPT-4.1 mini | Kimi K2 (Jul 2025) |
|---|---|---|
| Kagi LLM Benchmark | 48.6% | 64.4% |
| LMArena Hard Prompts | 1349 | 1384 |
| Epoch Capabilities Index | 135.01 | 146.01 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 26.3% |
| ARC-AGI-1 | 3.5% | — |
| CritPt | 0% | — |
| Chess Puzzles | 7% | — |
| Mystery Game Puzzles | 7% | — |
| DTBench | 68.8% | — |
| LMCA | 21.1% | — |
| ForecastBench | — | 60.2 |
Math Kimi K2 (Jul 2025) leads
GPT-4.1 mini: 24.1 (#270), Kimi K2 (Jul 2025): 42.7 (#83)
| Benchmark | GPT-4.1 mini | Kimi K2 (Jul 2025) |
|---|---|---|
| Omni-MATH | 49.1% | 65.4% |
| LMArena Math | 1343 | 1397 |
| FrontierMath (Feb 2025 set) | 4.5% | 21.4% |
| FrontierMath (Tiers 1-3) | 6.7% | — |
| OTIS Mock AIME 2024-2025 | 44.7% | — |
| MATH Level 5 | 87.3% | — |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Kimi K2 (Jul 2025) leads
GPT-4.1 mini: 34.7 (#194), Kimi K2 (Jul 2025): 37.3 (#157)
| Benchmark | GPT-4.1 mini | Kimi K2 (Jul 2025) |
|---|---|---|
| MMLU-Pro | 78.3% | 81.9% |
| GPQA (HELM) | 61.4% | 65.3% |
| LMArena Expert | 1338 | 1365 |
| GPQA Diamond | 65.8% | — |
| SimpleQA Verified | 12.7% | — |
| Confabulations | — | 20.4% |
| Vectara Hallucination Rate | — | 17.9% |
Multimodal Not comparable
GPT-4.1 mini: 35.8 (#82), Kimi K2 (Jul 2025): —
| Benchmark | GPT-4.1 mini | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Vision | 1181 | — |
Multilingual Kimi K2 (Jul 2025) leads
GPT-4.1 mini: 45.7 (#166), Kimi K2 (Jul 2025): 49.6 (#130)
| Benchmark | GPT-4.1 mini | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1318 | 1372 |
| LMArena Chinese | 1329 | 1415 |
| LMArena French | 1358 | 1379 |
| LMArena German | 1351 | 1387 |
| LMArena Japanese | 1290 | 1349 |
| LMArena Korean | 1298 | 1325 |
| LMArena Russian | 1324 | 1385 |
| LMArena Spanish | 1319 | 1386 |
Instruction Following GPT-4.1 mini leads
GPT-4.1 mini: 73.7 (#118), Kimi K2 (Jul 2025): 71.1 (#156)
| Benchmark | GPT-4.1 mini | Kimi K2 (Jul 2025) |
|---|---|---|
| IFEval | 90.4% | 85% |
| LMArena Instruction Following | 1333 | 1348 |
Long Context Kimi K2 (Jul 2025) leads
GPT-4.1 mini: 31.8 (#275), Kimi K2 (Jul 2025): 41.2 (#145)
| Benchmark | GPT-4.1 mini | Kimi K2 (Jul 2025) |
|---|---|---|
| Fiction.LiveBench | 44.4% | 66.7% |
| LMArena Longer Query | 1344 | 1353 |
| CL-bench | — | 17.6% |
Writing & Preference Kimi K2 (Jul 2025) leads
GPT-4.1 mini: 48.6 (#199), Kimi K2 (Jul 2025): 62.3 (#78)
| Benchmark | GPT-4.1 mini | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1340 | 1380 |
| LMArena Creative Writing | 1300 | 1350 |
| EQ-Bench Creative Writing | 1147 | 1666 |
| WildBench | 83.8% | 86.2% |
| LMArena Multi-Turn | 1354 | 1371 |
| Short-Story Creative Writing | — | 85.6% |
Frequently asked questions
Is GPT-4.1 mini better than Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 33.6 on the Noometry Index.
Which is cheaper, GPT-4.1 mini or Kimi K2 (Jul 2025)?
GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Kimi K2 (Jul 2025) lists at $0.57 and $2.30.
Is GPT-4.1 mini or Kimi K2 (Jul 2025) better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 30.6 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 (Jul 2025) share?
31 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Kimi K2 (Jul 2025) has 42.