BlogLLM Benchmark Scores as Published, Side by Side
Kimi K3.1 Pro: Benchmark Scores as Published
Every result the catalog holds for Kimi K3.1 Pro: 51 tests in 12 areas, from 3 pages. All were printed by Moonshot AI itself. Each number is as printed; nothing is ranked or rescored.
Developer Moonshot AIReleased 2026-10-23Context window 1MData version 2026103001, as of 2026-10-30
Knowledge Work
Agentic Coding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| DeepSWE v1.1 | 75.5% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Harness: Claude Code; Dataset revision: v1.1 |
| Terminal-Bench 4.0 | 65.7% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Harness: Claude Code |
| ProgramBench Almost@1 | 31.5% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Harness: Claude Code |
| SWE-Marathon | 51.7% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Harness: Claude Code; Dataset revision: v1.1 |
| Kimi Code Bench 2.0 | 77.1% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Harness: Claude Code |
| Kimi Code Bench 3.0 Long-horizon | 61.2% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Harness: Claude Code |
ML Engineering
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| PostTrainBench v1.2 | 36.5% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Harness: Claude Code; Dataset revision: v1.2 |
Science and Math
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPQA Diamond | 94.2% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max |
| Terminal-Bench Science 0.1 | 38.1% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Harness: Claude Code |
| BioMysteryBench | 80.6% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Harness: Kimi Code |
Computer Use
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| OSWorld 2.1 partial | 79.6% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Harness: Kimi Agent |
Multimodal Understanding
Cybersecurity
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| ExploitBench | 74.7% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Harness: ExploitBench official harness; Attempt budget: 300 turns; pass@5 |
| ExploitGym | 20.7% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Harness: Kimi Code; Attempt budget: 6-hour wall-clock budget per task |
| xdev-bench-hard, problems solved (pass@3) | 81% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Harness: Kimi Code; Attempt budget: pass@3 |
| xdev-bench-hard, average success rate | 64.5% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Harness: Kimi Code; Attempt budget: pass@3 |
General Knowledge and Reasoning
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Humanity's Last Exam (no tools) | 51.1% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Tools: none |
| Humanity's Last Exam (with tools) | 70% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Tools: with tools |
| Humanity's Last Exam Diamond (no tools) | 39.4% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Tools: none |
| Kimi Hallu Bench Hard w/ tools (lower is better)lower is better | 8.3% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Tools: with tools |
| Kimi Hallu Bench w/o tools (lower is better)lower is better | 5.4% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Tools: none |
Tool Use and Workflows
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Agents' Last Exam (pass rate) | 43.2% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Harness: Kimi Code; Dataset revision: v1.1 |
| Agents' Last Exam (CLI) | 44.2% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Harness: Kimi Code; Dataset revision: v1.1 |
Web Search and Research
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| BrowseComp | 92.1% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max |
Instruction Following
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| HANDBOOK.md | 44.6% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Harness: OpenHands |
Engineering and Design
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| BenchCAD | 92.7% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Harness: Claude Code; Tools: with tools |
| Design Bench (Internal, Elo) | 957 | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max |
| BenchCAD w/o tools | 72.8% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Tools: none |
Price
API list prices in US dollars per one million tokens, as printed on the developer's pricing page on the day checked. Cost per task is measured by Vals AI.
| Price | Value | Printed by | Setup as printed |
|---|---|---|---|
| Input | $2 | Moonshot AI, Kimi API pricing (international platform)checked 2026-10-24 | - |
| Cached input | $0.2 | Moonshot AI, Kimi API pricing (international platform)checked 2026-10-24 | - |
| Cache write | $2 | Moonshot AI, Kimi API pricing (international platform)checked 2026-10-24 | Cache: 5 minute cache |
| Cache write, 1 hour | $4 | Moonshot AI, Kimi API pricing (international platform)checked 2026-10-24 | - |
| Output | $10 | Moonshot AI, Kimi API pricing (international platform)checked 2026-10-24 | - |
| Cost per taskVals AI, USD, lower is better | $7.49 | Vals AI, Vibe Code Bench v1.1 leaderboardchecked 2026-10-27 | Harness: OpenHands |
Side by side
More from Moonshot AI
Every number here is read from the same catalog file as the benchmark table, data version 2026103001. Where one page printed the model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.