Kimi K3.1 Pro
| Released | 2026-10-23 |
|---|---|
| Price per 1M | $2.00 in · $10.00 out |
| Overall score | 62.2 · rank 16 |
| Context window | 1,048,576 tokens |
| Provider | Moonshot AI |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 62.2 | 16 | 40 |
| Overall: Coding | 61.6 | 17 | 27 |
| Overall: Reasoning | 62.6 | 19 | 17 |
| Overall: Agentic work | 62.4 | 15 | 24 |
| Overall: Frontend | 60.5 | 17 | 7 |
| Coding | 61.1 | 20 | 4 |
| Agents | 62.6 | 10 | 11 |
| Reasoning | 63.8 | 19 | 9 |
| Math | 62.2 | 19 | 6 |
| Knowledge | 60.5 | 22 | 2 |
| Frontend | 60.2 | 17 | 3 |
| General | 64.8 | 9 | 5 |
| Value vs price | +10.3 | 29 |
Buzz
| Posts on X | About 62 a day |
|---|---|
| Mood | 18% positive, 12% negative |
| Hacker News | 14 mentions this week |
| Checked | 2026-11-11 |
- CAN AI BUILD BETTER AI? Of the 27 models tested on @ValsAI's AI research eval, only 7 were able to improve the trained model they were given on a fixed compute budget and none of them were open models. Claude Fable 5.2 had the highest score at 37.88, while the best open model w…
- sokobanteg v0.2 live gpt-6.1 sol, gpt-6.1 terra, gpt-6 astra claude opus 5.5, claude sonnet 5.5, claude haiku 5.5, claude fable 5.2 gemini 4 argon, gemini 4 carbon qwen3.8 max 0902, kimi k3.1 pro, muse wonder, muse ember, grok 4.7 build https://t.co/tv7RNPSEVT
- Cybersecurity agents need the full picture: code, crash logs and screenshots. Now on Infron: • Kimi K3.1 Pro Cyber for vulnerability research. • HY4 Uncensored for visual triage + remediation. 1M context + tool calling on both. https://t.co/m3vBH42f1Z https://t.co/giVcR05gvh h…
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 63.3 ±1.8 | 15 |
| High | 63.4 ±5.3 | 3 |
| Max | 62.0 ±1.3 | 22 |
| Extra High | 59.5 ±5.6 | 1 |
Evidence
Coding 61.1 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveBench 2.0 Coding | 67.8% | LiveBench | 2026-11-06 |
| WeirdML v3 | 9.9% | Epoch AI | 2026-11-11 |
| IOI | 81.9% | Vals AI | 2026-10-29 |
| SciCode | 60.8% | Epoch AI | 2026-11-11 |
Agents 62.6 ±0.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4.0 (Vals run) | 63.6% | Vals AI | 2026-11-09 |
| SRE Bench | 27.1% | Vals AI | 2026-11-05 |
| Terminal-Bench-Science | 31.4% | Vals AI | 2026-11-09 |
| APEX-Agents | 65.5% | Epoch AI | 2026-11-11 |
| LiveBench 2.0 Agentic | 38.7% | LiveBench | 2026-11-06 |
| LiveBench 2.0 Browser Use | 75.9% | LiveBench | 2026-11-06 |
| EMB v1.1 (Excel financial modeling) | 70.0% | Vals AI | 2026-11-09 |
| LiveBench 2.0 Research | 82.1% | LiveBench | 2026-11-06 |
| Tax Agent Bench | 24.9% | Vals AI | 2026-11-09 |
| Finance Agent v2.1 | 61.5% | Vals AI | 2026-11-09 |
| HLAB-Vals 1.1 (legal agent) | 11.7% | Vals AI | 2026-11-09 |
Reasoning 63.8 ±1.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 93.4% | Lech Mazur | 2026-11-10 |
| MysteryMechanism | 26.1% | Vals AI | 2026-11-09 |
| GPQA Diamond | 94.2% | Epoch AI | 2026-11-06 |
| CritPt | 24.6% | Epoch AI | 2026-11-11 |
| BioMysteryBench | 75.6% | Vals AI | 2026-11-09 |
| Chess Puzzles | 45.0% | Epoch AI | 2026-11-06 |
| LiveBench 2.0 Reasoning | 91.1% | LiveBench | 2026-11-06 |
| Mystery Game Puzzles | 42.0% | Epoch AI | 2026-11-06 |
| LiveBench 2.0 Data Analysis | 79.1% | LiveBench | 2026-11-06 |
Math 62.2 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 78.3% | Epoch AI | 2026-11-06 |
| FrontierMath Tier 4 | 65.9% | Epoch AI | 2026-11-06 |
| MathArena ArXivMath (latest month) | 45.7% | MathArena | 2026-11-11 |
| OTIS Mock AIME 2024-2025 | 100.0% | Epoch AI | 2026-11-06 |
| ProofBench v1.1 | 91.0% | Vals AI | 2026-11-09 |
| ProofBench | 91.0% | Epoch AI | 2026-11-11 |
| MathArena BrokenArXiv (latest month) | 58.0% | MathArena | 2026-11-11 |
Knowledge 60.5 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 62.2% | Epoch AI | 2026-11-06 |
| Legal Research Bench | 37.5% | Vals AI | 2026-11-09 |
Frontend 60.2 ±2.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveBench 2.0 Design | 73.7% | LiveBench | 2026-11-06 |
| Vibe Code Bench v1.1 | 84.9% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,688 | LMArena | 2026-11-09 |
General 64.8 ±4.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LLM Debate Benchmark | 1,603 | Lech Mazur | 2026-10-26 |
| EQ-Bench Creative Writing v3 | 2,173 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,483 | LMArena | 2026-11-09 |
| Creative Story-Writing (Lech Mazur) | 85.0% | Lech Mazur | 2026-10-23 |
| EQ-Bench Longform Creative Writing | 79.9% | EQ-Bench | 2026-11-11 |
Names matched to this model
kimi-k3-1-pro, kimi-k3-1-pro-highspeed, kimi-k3-1-pro-together