GPT-6.1 Sol vs Kimi K3
| Spec | GPT-6.1 Sol | Kimi K3 |
|---|---|---|
| Respan Index | 69.7 (#12) | 52.8 (#35) |
| Blended price per 1M | $4 | $2.52 |
| Context window | 1.1M | 1.0M |
| Input / output per 1M | $2 / $10 | $0.192 / $9.5 |
| Max output | 128K | 1.0M |
| Input | text, vision | text, vision |
| Released | 2026-09-29 | 2026-07-16 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | GPT-6.1 Sol | Kimi K3 |
|---|---|---|
| Coding | 52.7 GPT-6.1 Sol | 38.8 Kimi K3 |
| Agents | 72.9 GPT-6.1 Sol | 61.8 Kimi K3 |
| Reasoning | 87.6 GPT-6.1 Sol | 54.8 Kimi K3 |
| Knowledge & language | 74.4 GPT-6.1 Sol | 52.9 Kimi K3 |
| Human preference | 59.7 GPT-6.1 Sol | 57.7 Kimi K3 |
Benchmarks both report
GPT-6.1 Sol leads on 21 of the 25 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | GPT-6.1 Sol | Kimi K3 |
|---|---|---|
| LMArena WebDev (LMArena) | 1743 | 1659 |
| LMArena Elo | 1483 | 1488 |
| LMArena Agent (LMArena) | 0.1131 | -0.0015 |
| Vending-Bench 2 (Andon Labs) | 12860.61 | 5165.04 |
| MirrorCode (Epoch AI) | 61.1% | 54.4% |
| SAGE 1.1 (Vals AI) | 90.5% | 86.8% |
| Chess Puzzles (Epoch AI) | 68% | 37% |
| APEX-Agents (Mercor) | 60% | 47.8% |
| FrontierMath Tier 4 v2 (Epoch AI) | 100% | 39% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 93.7% | 72.2% |
| Furniture Assembly (Epoch AI) | 80% | 34.2% |
| GPQA Diamond | 95.4% | 93.5% |
| LiveBench Agentic Coding (LiveBench) | 56.8% | 62.2% |
| LiveBench Coding (LiveBench) | 80.7% | 81.4% |
| LiveBench Data Analysis (LiveBench) | 82.7% | 78.7% |
| LiveBench Instruction Following (LiveBench) | 74.2% | 71.4% |
| LiveBench Language (LiveBench) | 90.1% | 85.5% |
| LiveBench Mathematics (LiveBench) | 96.8% | 84.4% |
| LiveBench Reasoning (LiveBench) | 92.6% | 90.7% |
| Mystery Game Puzzles (Epoch AI) | 80% | 26% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 97.2% |
| SAGE (Vals AI) | 46.5% | 52.8% |
| SimpleQA Verified | 73.9% | 50.6% |
| Terminal-Bench 4.0 (Vals AI) | 55.1% | 17.2% |
| SimpleBench (SimpleBench) | 82.9% | 60.7% |
FAQ
Is GPT-6.1 Sol better than Kimi K3?
GPT-6.1 Sol scores 69.7 on the Respan Index (#12), ahead of Kimi K3 at 52.8 (#35). GPT-6.1 Sol leads on 21 of the 25 benchmarks both report.
Which is cheaper, GPT-6.1 Sol or Kimi K3?
GPT-6.1 Sol lists at $2 input and $10 output per 1M tokens; Kimi K3 at $0.192 and $9.5. Kimi K3 is 1.6x cheaper per token at list price.
Which has the larger context window?
GPT-6.1 Sol accepts 1.1M tokens and Kimi K3 1.0M tokens.