Model comparison
GPT-6 Sol vs Kimi K3
GPT-6 Sol is the stronger model overall, scoring 61.8 to 59.5 on the Noometry Index.
Last verified . 42 shared benchmarks.
Summary
- They share 42 benchmarks with published results for both. GPT-6 Sol scores higher in 4 categories and Kimi K3 in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 74.2.
- The biggest single-benchmark swing is FrontierMath Tier 4: 90% for GPT-6 Sol and 39% for Kimi K3.
- GPT-6 Sol is cheaper at $2 / $10 per million input/output tokens, against $3 / $15 for Kimi K3.
- GPT-6 Sol accepts more context: 1.05M tokens versus 1.05M.
- Kimi K3 has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Sol | Kimi K3 | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 61.8 | 59.5 |
| Released | 2026-09-22 | 2026-07-16 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 1.05M |
| Max output | 128K | 1.05M |
| Input $ / M tokens | $2 | $3 |
| Output $ / M tokens | $10 | $15 |
| Results tracked | 45 | 53 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-6 Sol: 60.1 (#11), Kimi K3: 61.0 (#10)
| Benchmark | GPT-6 Sol | Kimi K3 |
|---|---|---|
| DeepSWE | 68.8% | 68.5% |
| FrontierCode | 49.3% | 44.2% |
| LMArena WebDev | 1688 | 1654 |
| SciCode | 57.6% | 59.5% |
| LMArena Coding | 1447 | 1508 |
| ALE-Bench | 2,462 | 1,524 |
| FrontierSWE | — | 25.9% |
| WeirdML | — | 82.6% |
Agentic & Tool Use Kimi K3 leads
GPT-6 Sol: 37.2 (#36), Kimi K3: 41.8 (#20)
| Benchmark | GPT-6 Sol | Kimi K3 |
|---|---|---|
| APEX-Agents | 54.3% | 50.6% |
| GDP.pdf | 26.4% | 19% |
| Vending-Bench 2 | 14,428 | 5,165 |
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 32% |
| GBAEval | — | 48.3% |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 74.0 (#9), Kimi K3: 63.0 (#17)
| Benchmark | GPT-6 Sol | Kimi K3 |
|---|---|---|
| ARC-AGI-2 | 89.6% | 60.4% |
| NYT Connections (extended) | 90.1% | 93.6% |
| ARC-AGI-1 | 95.5% | 94.5% |
| CritPt | 30.9% | 23.4% |
| LMArena Hard Prompts | 1418 | 1496 |
| Mystery Game Puzzles | 56% | 26% |
| DTBench | 97.3% | 91.2% |
| LMCA | 59.1% | 52.7% |
| Epoch Capabilities Index | 162.72 | 157.45 |
| SimpleBench | — | 60.7% |
| Chess Puzzles | — | 39% |
| EBR-Bench | 53.3% | — |
| Surface Evolver Bench | — | 95% |
| ForecastBench | — | 61.1 |
Math GPT-6 Sol leads
GPT-6 Sol: 87.2 (#7), Kimi K3: 74.2 (#16)
| Benchmark | GPT-6 Sol | Kimi K3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 89.8% | 72.2% |
| FrontierMath Tier 4 | 90% | 39% |
| OTIS Mock AIME 2024-2025 | 100% | 97.2% |
| ProofBench | 83% | 87% |
| LMArena Math | 1402 | 1491 |
| MathArena Final-Answer Competitions | — | 87.8% |
Knowledge GPT-6 Sol leads
GPT-6 Sol: 64.8 (#15), Kimi K3: 63.2 (#21)
| Benchmark | GPT-6 Sol | Kimi K3 |
|---|---|---|
| GPQA Diamond | 94.3% | 93.1% |
| SimpleQA Verified | 60.7% | 50.6% |
| LMArena Expert | 1439 | 1521 |
| Vectara Hallucination Rate | 6.5% | — |
Multimodal GPT-6 Sol leads
GPT-6 Sol: 47.6 (#10), Kimi K3: 37.8 (#70)
| Benchmark | GPT-6 Sol | Kimi K3 |
|---|---|---|
| Blueprint-Bench 2 | 36.9% | 29.5% |
| Furniture Assembly | 58.3% | 34.2% |
| LMArena Vision | 1245 | — |
Multilingual Kimi K3 leads
GPT-6 Sol: 50.5 (#118), Kimi K3: 56.3 (#21)
| Benchmark | GPT-6 Sol | Kimi K3 |
|---|---|---|
| LMArena Non-English | 1385 | 1466 |
| LMArena Chinese | 1405 | 1529 |
| LMArena French | 1410 | 1491 |
| LMArena German | 1390 | 1488 |
| LMArena Japanese | 1385 | 1487 |
| LMArena Korean | 1341 | 1458 |
| LMArena Russian | 1401 | 1482 |
| LMArena Spanish | 1384 | 1472 |
Instruction Following Kimi K3 leads
GPT-6 Sol: 74.5 (#94), Kimi K3: 77.7 (#14)
| Benchmark | GPT-6 Sol | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | 1412 | 1483 |
Long Context Kimi K3 leads
GPT-6 Sol: 43.1 (#108), Kimi K3: 45.8 (#29)
| Benchmark | GPT-6 Sol | Kimi K3 |
|---|---|---|
| LMArena Longer Query | 1411 | 1494 |
Writing & Preference Kimi K3 leads
GPT-6 Sol: 71.9 (#18), Kimi K3: 76.6 (#4)
| Benchmark | GPT-6 Sol | Kimi K3 |
|---|---|---|
| LMArena Text | 1395 | 1476 |
| LMArena Creative Writing | 1378 | 1454 |
| EQ-Bench Creative Writing | 2125 | 2082 |
| LMArena Multi-Turn | 1412 | 1488 |
| EQ-Bench 4 | — | 1339 |
Frequently asked questions
Is GPT-6 Sol better than Kimi K3?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 59.5 on the Noometry Index.
Which is cheaper, GPT-6 Sol or Kimi K3?
GPT-6 Sol is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Kimi K3 lists at $3 and $15.
Is GPT-6 Sol or Kimi K3 better for coding?
They score almost the same on coding (60.1 vs 61.0); test both on your own repository before choosing.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 1.05M.
How many benchmarks do GPT-6 Sol and Kimi K3 share?
42 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and Kimi K3 has 53.