Model comparison
GPT-6 Sol vs Kimi K2.5
GPT-6 Sol is the stronger model overall, scoring 49.2 to 47.8 on the Noometry Index. Kimi K2.5 costs 4.4× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. GPT-6 Sol scores higher in 4 categories and Kimi K2.5 in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 49.3 to 31.2.
- The biggest single-benchmark swing is NYT Connections (extended): 90.1% for GPT-6 Sol and 69.9% 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 Sol.
- GPT-6 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 Sol | Kimi K2.5 | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 49.2 | 47.8 |
| Released | 2026-09-22 | 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 | 22 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
GPT-6 Sol: 59.6 (#11), Kimi K2.5: 48.7 (#48)
| Benchmark | GPT-6 Sol | Kimi K2.5 |
|---|---|---|
| LMArena WebDev | 1692 | 1436 |
| LMArena Coding | 1453 | 1474 |
| SWE-bench Verified | — | 73.8% |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| SWE-bench Verified (bash only) | — | 70.8% |
| SWE-bench Multilingual | — | 67.3% |
| SciCode | — | 49% |
| WeirdML | — | 45.6% |
| ALE-Bench | — | 821.65 |
Agentic & Tool Use Too close to call
GPT-6 Sol: 33.5 (#49), Kimi K2.5: 34.0 (#44)
| Benchmark | GPT-6 Sol | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | — | 43.2% |
| OSWorld | — | 63.3% |
| GDP.pdf | 28% | — |
| Vending-Bench 2 | — | 1,198 |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 49.3 (#34), Kimi K2.5: 31.2 (#74)
| Benchmark | GPT-6 Sol | Kimi K2.5 |
|---|---|---|
| NYT Connections (extended) | 90.1% | 69.9% |
| LMArena Hard Prompts | 1420 | 1454 |
| ARC-AGI-2 | — | 11.8% |
| SimpleBench | — | 46.8% |
| Kagi LLM Benchmark | — | 78.5% |
| ARC-AGI-1 | — | 65.3% |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| EnigmaEval | — | 3.4% |
| Thematic Generalization | — | 69.4% |
| EBR-Bench | 53.3% | — |
| Epoch Capabilities Index | — | 148.05 |
Math Kimi K2.5 leads
GPT-6 Sol: 35.8 (#135), Kimi K2.5: 50.3 (#46)
| Benchmark | GPT-6 Sol | Kimi K2.5 |
|---|---|---|
| LMArena Math | 1404 | 1470 |
| MathArena Final-Answer Competitions | — | 62.3% |
| OTIS Mock AIME 2024-2025 | — | 92.2% |
| FrontierMath (Feb 2025 set) | — | 27.9% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Kimi K2.5 leads
GPT-6 Sol: 43.0 (#87), Kimi K2.5: 53.6 (#52)
| Benchmark | GPT-6 Sol | Kimi K2.5 |
|---|---|---|
| Vectara Hallucination Rate | 6.5% | 14.2% |
| LMArena Expert | 1449 | 1466 |
| GPQA Diamond | — | 87.6% |
| Humanity's Last Exam | — | 24.4% |
| SimpleQA Verified | — | 34.3% |
Multimodal GPT-6 Sol leads
GPT-6 Sol: 47.6 (#9), Kimi K2.5: 40.4 (#37)
| Benchmark | GPT-6 Sol | Kimi K2.5 |
|---|---|---|
| LMArena Vision | — | 1269 |
| Furniture Assembly | 58.3% | — |
| LMArena Document | — | 1430 |
Multilingual Kimi K2.5 leads
GPT-6 Sol: 51.0 (#113), Kimi K2.5: 54.1 (#50)
| Benchmark | GPT-6 Sol | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1389 | 1433 |
| LMArena Chinese | 1416 | 1495 |
| LMArena Russian | 1407 | 1436 |
| LMArena Spanish | 1377 | 1450 |
| LMArena French | — | 1454 |
| LMArena German | — | 1441 |
| LMArena Japanese | — | 1422 |
| LMArena Korean | — | 1412 |
Instruction Following Kimi K2.5 leads
GPT-6 Sol: 74.4 (#97), Kimi K2.5: 75.5 (#60)
| Benchmark | GPT-6 Sol | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1431 |
Long Context Kimi K2.5 leads
GPT-6 Sol: 43.2 (#100), Kimi K2.5: 52.1 (#7)
| Benchmark | GPT-6 Sol | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1415 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 72.3 (#15), Kimi K2.5: 65.3 (#51)
| Benchmark | GPT-6 Sol | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1396 | 1445 |
| LMArena Creative Writing | 1392 | 1423 |
| EQ-Bench Creative Writing | 2125 | 1579 |
| LMArena Multi-Turn | 1405 | 1444 |
Frequently asked questions
Is GPT-6 Sol better than Kimi K2.5?
GPT-6 Sol is the stronger model overall, scoring 49.2 to 47.8 on the Noometry Index. Kimi K2.5 costs 4.4× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Which is cheaper, GPT-6 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 Sol lists at $2 and $10.
Is GPT-6 Sol or Kimi K2.5 better for coding?
GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 48.7 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 262K.
How many benchmarks do GPT-6 Sol and Kimi K2.5 share?
17 benchmarks have published results for both models. GPT-6 Sol has 22 scored results on Noometry and Kimi K2.5 has 51.