Model comparison
GPT-5.1 vs Kimi K2 (Jul 2025)
GPT-5.1 is the stronger model overall, scoring 49.0 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 3.4× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. GPT-5.1 scores higher in 9 categories and Kimi K2 (Jul 2025) in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.1 leads 39.8 to 23.3.
- The biggest single-benchmark swing is SimpleBench: 53.2% for GPT-5.1 and 26.3% for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- GPT-5.1 accepts more context: 400K tokens versus 262K.
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.
Side by side
| GPT-5.1 | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 49.0 | 41.2 |
| Released | 2025-11-13 | 2025-07-12 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 128K | 262K |
| Input $ / M tokens | $1.25 | $0.57 |
| Output $ / M tokens | $10 | $2.30 |
| Results tracked | 63 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
GPT-5.1: 46.4 (#66), Kimi K2 (Jul 2025): 42.4 (#102)
| Benchmark | GPT-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| SWE-bench Verified (bash only) | 66% | 63.4% |
| GSO | 13.7% | 4.9% |
| WeirdML | 60.8% | 42.8% |
| LMArena Coding | 1454 | 1399 |
| ALE-Bench | 1,192 | 597.5 |
| SWE-bench Verified | 68% | — |
| Aider Polyglot | — | 59.1% |
| LMArena WebDev | 1395 | — |
| SciCode | 43.3% | — |
| LiveBench Coding | 72.5% | — |
Agentic & Tool Use Too close to call
GPT-5.1: 32.7 (#60), Kimi K2 (Jul 2025): 32.4 (#64)
| Benchmark | GPT-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | 47.6% | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| DeepResearch Bench | 42.8% | — |
| LMArena Search | 1199 | — |
| METR Time Horizons | — | 59.2% |
| Vending-Bench 2 | 1,473 | — |
Reasoning GPT-5.1 leads
GPT-5.1: 39.8 (#58), Kimi K2 (Jul 2025): 23.3 (#179)
| Benchmark | GPT-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| SimpleBench | 53.2% | 26.3% |
| LMArena Hard Prompts | 1457 | 1384 |
| Epoch Capabilities Index | 149.64 | 146.01 |
| ForecastBench | 58.1 | 60.2 |
| ARC-AGI-2 | 17.6% | — |
| Kagi LLM Benchmark | — | 64.4% |
| ARC-AGI-1 | 72.8% | — |
| CritPt | 4.9% | — |
| Chess Puzzles | 32% | — |
| EnigmaEval | 11.2% | — |
| LiveBench Reasoning | 95.8% | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 90.1% | — |
| LiveBench Data Analysis | 72.1% | — |
| LMCA | 43.9% | — |
| LiveBench | 78.8% | — |
Math GPT-5.1 leads
GPT-5.1: 52.2 (#51), Kimi K2 (Jul 2025): 42.7 (#83)
| Benchmark | GPT-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| Omni-MATH | 46.4% | 65.4% |
| LMArena Math | 1447 | 1397 |
| FrontierMath (Feb 2025 set) | 31% | 21.4% |
| FrontierMath Tier 4 (v1) | 12.5% | 0% |
| OTIS Mock AIME 2024-2025 | 88.6% | — |
| LiveBench Math | 94.5% | — |
Knowledge GPT-5.1 leads
GPT-5.1: 50.6 (#71), Kimi K2 (Jul 2025): 37.3 (#157)
| Benchmark | GPT-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| MMLU-Pro | 57.9% | 81.9% |
| Vectara Hallucination Rate | 10.9% | 17.9% |
| GPQA (HELM) | 44.2% | 65.3% |
| LMArena Expert | 1470 | 1365 |
| GPQA Diamond | 87.6% | — |
| Humanity's Last Exam | 23.7% | — |
| SimpleQA Verified | 48% | — |
| Confabulations | — | 20.4% |
Multimodal Not comparable
GPT-5.1: 44.8 (#19), Kimi K2 (Jul 2025): —
| Benchmark | GPT-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Vision | 1250 | — |
| VPCT | 58.7% | — |
| LMArena Document | 1403 | — |
Multilingual GPT-5.1 leads
GPT-5.1: 53.8 (#56), Kimi K2 (Jul 2025): 49.6 (#130)
| Benchmark | GPT-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1431 | 1372 |
| LMArena Chinese | 1495 | 1415 |
| LMArena French | 1450 | 1379 |
| LMArena German | 1438 | 1387 |
| LMArena Japanese | 1453 | 1349 |
| LMArena Korean | 1401 | 1325 |
| LMArena Russian | 1435 | 1385 |
| LMArena Spanish | 1433 | 1386 |
Instruction Following GPT-5.1 leads
GPT-5.1: 83.9 (#1), Kimi K2 (Jul 2025): 71.1 (#156)
| Benchmark | GPT-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| IFEval | 93.5% | 85% |
| LMArena Instruction Following | 1443 | 1348 |
| LiveBench Instruction Following | 93.3% | — |
Long Context GPT-5.1 leads
GPT-5.1: 47.6 (#14), Kimi K2 (Jul 2025): 41.2 (#145)
| Benchmark | GPT-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| CL-bench | 23.7% | 17.6% |
| LMArena Longer Query | 1447 | 1353 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench Life | 17.3% | — |
Writing & Preference GPT-5.1 leads
GPT-5.1: 64.5 (#55), Kimi K2 (Jul 2025): 62.3 (#78)
| Benchmark | GPT-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1443 | 1380 |
| LMArena Creative Writing | 1427 | 1350 |
| WildBench | 86.3% | 86.2% |
| LMArena Multi-Turn | 1450 | 1371 |
| Short-Story Creative Writing | — | 85.6% |
| EQ-Bench Creative Writing | — | 1666 |
| LiveBench Language | 80.2% | — |
Frequently asked questions
Is GPT-5.1 better than Kimi K2 (Jul 2025)?
GPT-5.1 is the stronger model overall, scoring 49.0 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 3.4× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Which is cheaper, GPT-5.1 or Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; GPT-5.1 lists at $1.25 and $10.
Is GPT-5.1 or Kimi K2 (Jul 2025) better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.4 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
GPT-5.1 does, with 400K tokens against 262K.
How many benchmarks do GPT-5.1 and Kimi K2 (Jul 2025) share?
34 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and Kimi K2 (Jul 2025) has 42.