Model comparison
GPT-5.1 vs Kimi K2.5
GPT-5.1 and Kimi K2.5 score almost the same on the Noometry Index (49.0 vs 48.1), so choose on price, context window or the category you care about most.
Last verified . 43 shared benchmarks.
Summary
- They share 43 benchmarks with published results for both. GPT-5.1 scores higher in 4 categories and Kimi K2.5 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.1 leads 39.8 to 31.2.
- The biggest single-benchmark swing is Chess Puzzles: 32% for GPT-5.1 and 12% for Kimi K2.5.
- Kimi K2.5 is cheaper at $0.45 / $2.25 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- GPT-5.1 accepts more context: 400K tokens versus 262K.
- Kimi K2.5 has downloadable open weights; the other is API-only.
Side by side
| GPT-5.1 | Kimi K2.5 | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 49.0 | 48.1 |
| Released | 2025-11-13 | 2026-01-27 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 128K | 262K |
| Input $ / M tokens | $1.25 | $0.45 |
| Output $ / M tokens | $10 | $2.25 |
| Results tracked | 63 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
GPT-5.1: 46.4 (#66), Kimi K2.5: 48.8 (#53)
| Benchmark | GPT-5.1 | Kimi K2.5 |
|---|---|---|
| SWE-bench Verified | 68% | 73.8% |
| SWE-bench Verified (bash only) | 66% | 70.8% |
| LMArena WebDev | 1395 | 1437 |
| SciCode | 43.3% | 49% |
| WeirdML | 60.8% | 45.6% |
| LMArena Coding | 1454 | 1474 |
| ALE-Bench | 1,192 | 821.65 |
| SWE-bench Multilingual | — | 67.3% |
| GSO | 13.7% | — |
| LiveBench Coding | 72.5% | — |
Agentic & Tool Use Kimi K2.5 leads
GPT-5.1: 32.7 (#60), Kimi K2.5: 34.2 (#48)
| Benchmark | GPT-5.1 | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | 47.6% | 43.2% |
| Vending-Bench 2 | 1,473 | 1,198 |
| DeepResearch Bench | 42.8% | — |
| OSWorld | — | 63.3% |
| LMArena Search | 1199 | — |
Reasoning GPT-5.1 leads
GPT-5.1: 39.8 (#58), Kimi K2.5: 31.2 (#80)
| Benchmark | GPT-5.1 | Kimi K2.5 |
|---|---|---|
| ARC-AGI-2 | 17.6% | 11.8% |
| SimpleBench | 53.2% | 46.8% |
| ARC-AGI-1 | 72.8% | 65.3% |
| CritPt | 4.9% | 3.1% |
| Chess Puzzles | 32% | 12% |
| EnigmaEval | 11.2% | 3.4% |
| LMArena Hard Prompts | 1457 | 1453 |
| Epoch Capabilities Index | 149.64 | 148.03 |
| Kagi LLM Benchmark | — | 78.5% |
| NYT Connections (extended) | — | 69.9% |
| Thematic Generalization | — | 69.4% |
| LiveBench Reasoning | 95.8% | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 90.1% | — |
| LiveBench Data Analysis | 72.1% | — |
| LMCA | 43.9% | — |
| ForecastBench | 58.1 | — |
| LiveBench | 78.8% | — |
Math Too close to call
GPT-5.1: 52.2 (#51), Kimi K2.5: 51.8 (#53)
| Benchmark | GPT-5.1 | Kimi K2.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.6% | 92.2% |
| LMArena Math | 1447 | 1470 |
| FrontierMath (Feb 2025 set) | 31% | 27.9% |
| FrontierMath Tier 4 (v1) | 12.5% | 4.2% |
| MathArena Final-Answer Competitions | — | 62.3% |
| Omni-MATH | 46.4% | — |
| LiveBench Math | 94.5% | — |
Knowledge Kimi K2.5 leads
GPT-5.1: 50.6 (#71), Kimi K2.5: 53.6 (#56)
| Benchmark | GPT-5.1 | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | 87.6% | 87.6% |
| Humanity's Last Exam | 23.7% | 24.4% |
| SimpleQA Verified | 48% | 34.3% |
| Vectara Hallucination Rate | 10.9% | 14.2% |
| LMArena Expert | 1470 | 1466 |
| MMLU-Pro | 57.9% | — |
| GPQA (HELM) | 44.2% | — |
Multimodal GPT-5.1 leads
GPT-5.1: 44.8 (#19), Kimi K2.5: 41.1 (#39)
| Benchmark | GPT-5.1 | Kimi K2.5 |
|---|---|---|
| LMArena Vision | 1250 | 1269 |
| LMArena Document | 1403 | 1430 |
| VPCT | 58.7% | — |
Multilingual Too close to call
GPT-5.1: 53.8 (#56), Kimi K2.5: 53.9 (#53)
| Benchmark | GPT-5.1 | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1431 | 1433 |
| LMArena Chinese | 1495 | 1495 |
| LMArena French | 1450 | 1454 |
| LMArena German | 1438 | 1441 |
| LMArena Japanese | 1453 | 1421 |
| LMArena Korean | 1401 | 1410 |
| LMArena Russian | 1435 | 1435 |
| LMArena Spanish | 1433 | 1450 |
Instruction Following GPT-5.1 leads
GPT-5.1: 83.9 (#1), Kimi K2.5: 75.3 (#64)
| Benchmark | GPT-5.1 | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1443 | 1431 |
| LiveBench Instruction Following | 93.3% | — |
| IFEval | 93.5% | — |
Long Context Kimi K2.5 leads
GPT-5.1: 47.6 (#14), Kimi K2.5: 52.1 (#7)
| Benchmark | GPT-5.1 | Kimi K2.5 |
|---|---|---|
| CL-bench | 23.7% | 19.3% |
| CL-bench Life | 17.3% | 13.2% |
| LMArena Longer Query | 1447 | 1445 |
| Fiction.LiveBench | — | 86.1% |
Writing & Preference Too close to call
GPT-5.1: 64.5 (#55), Kimi K2.5: 65.1 (#53)
| Benchmark | GPT-5.1 | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1443 | 1445 |
| LMArena Creative Writing | 1427 | 1423 |
| LMArena Multi-Turn | 1450 | 1444 |
| EQ-Bench Creative Writing | — | 1579 |
| WildBench | 86.3% | — |
| LiveBench Language | 80.2% | — |
Frequently asked questions
Is GPT-5.1 better than Kimi K2.5?
GPT-5.1 and Kimi K2.5 score almost the same on the Noometry Index (49.0 vs 48.1), so choose on price, context window or the category you care about most.
Which is cheaper, GPT-5.1 or Kimi K2.5?
Kimi K2.5 is cheaper. It lists at $0.45 per million input tokens and $2.25 per million output tokens; GPT-5.1 lists at $1.25 and $10.
Is GPT-5.1 or Kimi K2.5 better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 46.4 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 K2.5 share?
43 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and Kimi K2.5 has 51.