Model comparison
GPT-6.1 Sol vs Kimi K2.5
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 48.1 on the Noometry Index. Kimi K2.5 costs 4.4× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. GPT-6.1 Sol scores higher in 8 categories and Kimi K2.5 in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6.1 Sol leads 81.9 to 31.2.
- The biggest single-benchmark swing is ARC-AGI-2: 94.2% for GPT-6.1 Sol and 11.8% for Kimi K2.5.
- Kimi K2.5 is cheaper at $0.45 / $2.25 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 262K.
- Kimi K2.5 has downloadable open weights; the other is API-only.
Side by side
| GPT-6.1 Sol | Kimi K2.5 | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 65.6 | 48.1 |
| Released | 2026-09-29 | 2026-01-27 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 262K |
| Input $ / M tokens | $2 | $0.45 |
| Output $ / M tokens | $10 | $2.25 |
| Results tracked | 34 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6.1 Sol leads
GPT-6.1 Sol: 63.2 (#8), Kimi K2.5: 48.8 (#53)
| Benchmark | GPT-6.1 Sol | Kimi K2.5 |
|---|---|---|
| LMArena WebDev | 1755 | 1437 |
| SciCode | 55.8% | 49% |
| LMArena Coding | 1487 | 1474 |
| SWE-bench Verified | — | 73.8% |
| DeepSWE | 75.2% | — |
| FrontierCode | 50.2% | — |
| SWE-bench Verified (bash only) | — | 70.8% |
| SWE-bench Multilingual | — | 67.3% |
| WeirdML | — | 45.6% |
| ALE-Bench | — | 821.65 |
Agentic & Tool Use GPT-6.1 Sol leads
GPT-6.1 Sol: 39.6 (#26), Kimi K2.5: 34.2 (#48)
| Benchmark | GPT-6.1 Sol | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | — | 43.2% |
| APEX-Agents | 60% | — |
| OSWorld | — | 63.3% |
| GDP.pdf | 32% | — |
| Vending-Bench 2 | — | 1,198 |
Reasoning GPT-6.1 Sol leads
GPT-6.1 Sol: 81.9 (#2), Kimi K2.5: 31.2 (#80)
| Benchmark | GPT-6.1 Sol | Kimi K2.5 |
|---|---|---|
| ARC-AGI-2 | 94.2% | 11.8% |
| NYT Connections (extended) | 95.5% | 69.9% |
| ARC-AGI-1 | 98.5% | 65.3% |
| CritPt | 31.7% | 3.1% |
| Chess Puzzles | 61% | 12% |
| LMArena Hard Prompts | 1466 | 1453 |
| Epoch Capabilities Index | 166.09 | 148.03 |
| SimpleBench | — | 46.8% |
| Kagi LLM Benchmark | — | 78.5% |
| EnigmaEval | — | 3.4% |
| Thematic Generalization | — | 69.4% |
| EBR-Bench | 54.3% | — |
| Mystery Game Puzzles | 80% | — |
Math GPT-6.1 Sol leads
GPT-6.1 Sol: 93.7 (#1), Kimi K2.5: 51.8 (#53)
| Benchmark | GPT-6.1 Sol | Kimi K2.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 92.2% |
| LMArena Math | 1464 | 1470 |
| FrontierMath (Tiers 1-3) | 93.7% | — |
| FrontierMath Tier 4 | 100% | — |
| MathArena Final-Answer Competitions | — | 62.3% |
| ProofBench | 99% | — |
| FrontierMath (Feb 2025 set) | — | 27.9% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge GPT-6.1 Sol leads
GPT-6.1 Sol: 71.8 (#4), Kimi K2.5: 53.6 (#56)
| Benchmark | GPT-6.1 Sol | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | 95.4% | 87.6% |
| SimpleQA Verified | 73.9% | 34.3% |
| LMArena Expert | 1502 | 1466 |
| Humanity's Last Exam | — | 24.4% |
| Vectara Hallucination Rate | — | 14.2% |
Multimodal GPT-6.1 Sol leads
GPT-6.1 Sol: 52.7 (#5), Kimi K2.5: 41.1 (#39)
| Benchmark | GPT-6.1 Sol | Kimi K2.5 |
|---|---|---|
| LMArena Vision | 1288 | 1269 |
| Furniture Assembly | 80% | — |
| LMArena Document | — | 1430 |
Multilingual Too close to call
GPT-6.1 Sol: 54.3 (#46), Kimi K2.5: 53.9 (#53)
| Benchmark | GPT-6.1 Sol | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1438 | 1433 |
| LMArena Chinese | 1477 | 1495 |
| LMArena Russian | 1455 | 1435 |
| LMArena French | — | 1454 |
| LMArena German | — | 1441 |
| LMArena Japanese | — | 1421 |
| LMArena Korean | — | 1410 |
| LMArena Spanish | — | 1450 |
Instruction Following GPT-6.1 Sol leads
GPT-6.1 Sol: 77.0 (#29), Kimi K2.5: 75.3 (#64)
| Benchmark | GPT-6.1 Sol | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1468 | 1431 |
Long Context Kimi K2.5 leads
GPT-6.1 Sol: 44.9 (#54), Kimi K2.5: 52.1 (#7)
| Benchmark | GPT-6.1 Sol | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1465 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |
Writing & Preference Kimi K2.5 leads
GPT-6.1 Sol: 63.6 (#63), Kimi K2.5: 65.1 (#53)
| Benchmark | GPT-6.1 Sol | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1447 | 1445 |
| LMArena Creative Writing | 1432 | 1423 |
| LMArena Multi-Turn | 1449 | 1444 |
| EQ-Bench Creative Writing | — | 1579 |
Frequently asked questions
Is GPT-6.1 Sol better than Kimi K2.5?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 48.1 on the Noometry Index. Kimi K2.5 costs 4.4× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Which is cheaper, GPT-6.1 Sol 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-6.1 Sol lists at $2 and $10.
Is GPT-6.1 Sol or Kimi K2.5 better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 48.8 in the Noometry coding category.
Which has the bigger context window?
GPT-6.1 Sol does, with 1.05M tokens against 262K.
How many benchmarks do GPT-6.1 Sol and Kimi K2.5 share?
24 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Kimi K2.5 has 51.