# Kimi K3.1 Pro vs Kimi K2.5 (Reasoning)

> Side-by-side benchmark comparison for Kimi K3.1 Pro and Kimi K2.5 (Reasoning) across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/kimi-3-1-pro-vs-kimi-k2-5-reasoning
- Last updated: October 23, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Kimi K3.1 Pro leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Kimi K3.1 Pro has the higher overall point estimate 82 to 56.02. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in multimodal & grounded, where the averages are 98 for Kimi K3.1 Pro and 69 for Kimi K2.5 (Reasoning).
- The biggest single benchmark swing is BrowseComp in Agentic, with scores of 92.1% and 60.6%.
- Kimi K2.5 (Reasoning) is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Kimi K3.1 Pro also has the larger context window at 1.05M.

## Model Snapshot

| Property | Kimi K3.1 Pro | Kimi K2.5 (Reasoning) |
|----------|----------|----------|
| Creator | Moonshot AI | Moonshot AI |
| Type | Pending | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1.05M | 128K |
| Overall Score | null | 56.02 |
| Benchmarks Covered | 42 | 15 |
| Pricing (input/output) | $2.00 / $10.00 | $0.60 / $3.00 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- Kimi K3.1 Pro public-lane score: Coming soon
- Kimi K2.5 (Reasoning) public-lane score: 38.5 (Estimated · #72/132)

| Benchmark | Kimi K3.1 Pro | Kimi K2.5 (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 4.0 | 65.70% | Coming soon | Coming soon |
| Terminal-Bench-Science 0.1 | 38.1% | Coming soon | Coming soon |
| HLE w/ tools | 70.0% | Coming soon | Coming soon |
| BrowseComp | 92.1% | 60.6% | Kimi K3.1 Pro |
| BioMysteryBench | 80.6% | Coming soon | Coming soon |
| Agents' Last Exam | 43.2% | Coming soon | Coming soon |
| Agents' Last Exam (CLI) | 44.2% | Coming soon | Coming soon |
| APEX-Agents | 67.2% | Coming soon | Coming soon |
| Frontier Finance | 58.6% | Coming soon | Coming soon |
| HANDBOOK.md | 44.6% | Coming soon | Coming soon |
| OSWorld 2.0 | 79.6% | Coming soon | Coming soon |
| Business Operation | 37.8% | Coming soon | Coming soon |
| Financial Modeling | 57.6% | Coming soon | Coming soon |
| Financial Research | 70.4% | Coming soon | Coming soon |
| Kimi Hallu Bench Hard (tools) | 8.3% | Coming soon | Coming soon |
| ExploitGym | 20.7% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 50.8% | Coming soon |
| OSWorld-Verified | Coming soon | 63.3% | Coming soon |
| Gert Labs | Coming soon | 32.58% | Coming soon |

### Coding

- Winner: Not comparable
- Kimi K3.1 Pro public-lane score: Coming soon
- Kimi K2.5 (Reasoning) public-lane score: Coming soon

| Benchmark | Kimi K3.1 Pro | Kimi K2.5 (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| DeepSWE | 75.5% | Coming soon | Coming soon |
| ProgramBench (binary) | 31.5% | Coming soon | Coming soon |
| Kimi Code Bench v2 | 77.1% | Coming soon | Coming soon |
| Kimi Code Bench 3.0 Long-horizon | 61.2% | Coming soon | Coming soon |
| sweMarathon | 51.7% | Coming soon | Coming soon |
| PostTrainBench v1.2 | 36.5% | Coming soon | Coming soon |
| SWE-bench Verified | Coming soon | 76.8% | Coming soon |
| LiveCodeBench v6 | Coming soon | 85.0% | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 50.8% | Coming soon |
| Vibe Code Bench | Coming soon | 17.54% | Coming soon |

### Reasoning

- Winner: Not comparable
- Kimi K3.1 Pro public-lane score: Coming soon
- Kimi K2.5 (Reasoning) public-lane score: 66.3 (Unranked · 1 rankable row)

| Benchmark | Kimi K3.1 Pro | Kimi K2.5 (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | Coming soon | 61% | Coming soon |

### Multimodal & Grounded

- Winner: Directional only
- Kimi K3.1 Pro public-lane score: 98 (#1/56)
- Kimi K2.5 (Reasoning) public-lane score: 69 (#35/56)

| Benchmark | Kimi K3.1 Pro | Kimi K2.5 (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| OfficeQA Pro | 67.4% | Coming soon | Coming soon |
| OfficeQA Pro v2 | 64.4% | Coming soon | Coming soon |
| BenchCAD Vision2Code (no tools) | 0.728 | Coming soon | Coming soon |
| BenchCAD Vision2Code (tools) | 0.927 | Coming soon | Coming soon |
| MMMU-Pro | 84.1% | 78.5% | Kimi K3.1 Pro |
| MMMU-Pro w/ Python | 90% | Coming soon | Coming soon |
| CharXiv | 93.4% | 77.5% | Kimi K3.1 Pro |
| CharXiv w/o tools | 89% | Coming soon | Coming soon |
| Chartography (tools) | 90.2% | Coming soon | Coming soon |
| BabyVision w/ Python | 95.4% | Coming soon | Coming soon |
| ZeroBench | 39.0% | Coming soon | Coming soon |
| ZeroBench w/ Python | 63.0% | Coming soon | Coming soon |
| GDP.pdf (Gemini judge) | 34.6% | Coming soon | Coming soon |
| GDP.pdf w/ Python (Gemini judge) | 85.7% | Coming soon | Coming soon |
| PerceptionBench | 68.3% | Coming soon | Coming soon |

### Knowledge

- Winner: Not comparable
- Kimi K3.1 Pro public-lane score: Coming soon
- Kimi K2.5 (Reasoning) public-lane score: 48.2 (Estimated · #87/187)

| Benchmark | Kimi K3.1 Pro | Kimi K2.5 (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 94.2% | 87.6% | Kimi K3.1 Pro |
| GPQA-D | 94.2% | Coming soon | Coming soon |
| HLE | 70% | Coming soon | Coming soon |
| HLE w/o tools | 51.1% | Coming soon | Coming soon |
| Kimi Hallu Bench | 5.4% | Coming soon | Coming soon |
| MMLU-Pro | Coming soon | 87.1% | Coming soon |

### Mathematics

- Winner: Not comparable
- Kimi K3.1 Pro public-lane score: Coming soon
- Kimi K2.5 (Reasoning) public-lane score: Coming soon

| Benchmark | Kimi K3.1 Pro | Kimi K2.5 (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| AIME 2025 | Coming soon | 96.1% | Coming soon |
| HMMT Feb 2025 | Coming soon | 95.4% | Coming soon |

## FAQ

### Which is better overall, Kimi K3.1 Pro or Kimi K2.5 (Reasoning)?

Kimi K3.1 Pro has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between Kimi K3.1 Pro and Kimi K2.5 (Reasoning)?

The widest category gap is in multimodal & grounded, where the averages are 98 for Kimi K3.1 Pro and 69 for Kimi K2.5 (Reasoning).

### How many benchmarks does Kimi K3.1 Pro cover on BenchLM?

Kimi K3.1 Pro currently has 42 sourced benchmark scores on BenchLM.

### How many benchmarks does Kimi K2.5 (Reasoning) cover on BenchLM?

Kimi K2.5 (Reasoning) currently has 15 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Kimi K3.1 Pro vs Kimi K2.5](/compare/kimi-3-1-pro-vs-kimi-k2-5)
- [Kimi K2.5 (Reasoning) vs Kimi K2.5](/compare/kimi-k2-5-vs-kimi-k2-5-reasoning)
- [Kimi K3.1 Pro vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-kimi-3-1-pro)
- [Kimi K2.5 (Reasoning) vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-kimi-k2-5-reasoning)

## Explore More

- [Kimi K3.1 Pro profile](/models/kimi-3-1-pro)
- [Kimi K2.5 (Reasoning) profile](/models/kimi-k2-5-reasoning)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)