# GLM-4.7 vs Kimi K2

> Side-by-side benchmark comparison for GLM-4.7 and Kimi K2 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/glm-4-7-vs-kimi-k2
- Last updated: October 17, 2026

- Shared sourced benchmarks: 6
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

GLM-4.7 leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- GLM-4.7 has the higher overall point estimate 48.85 to 33.48. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in instruction following, where the averages are 82.8 for GLM-4.7 and 48.4 for Kimi K2.
- The biggest single benchmark swing is AIME 2025 in Mathematics, with scores of 95.7% and 49.5%.
- GLM-4.7 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- GLM-4.7 also has the larger context window at 200K.

## Model Snapshot

| Property | GLM-4.7 | Kimi K2 |
|----------|----------|----------|
| Creator | Z.AI | Moonshot AI |
| Type | Open Weight | Proprietary |
| Reasoning | Reasoning | Non-Reasoning |
| Context | 200K | 128K |
| Overall Score | 48.85 | 33.48 |
| Benchmarks Covered | 17 | 13 |
| Pricing (input/output) | $0.00 / $0.00 | $0.60 / $2.50 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- GLM-4.7 public-lane score: 31.6 (Estimated · #91/128)
- Kimi K2 public-lane score: Coming soon

| Benchmark | GLM-4.7 | Kimi K2 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 41% | Coming soon | Coming soon |
| BrowseComp | 52% | Coming soon | Coming soon |
| VITA-Bench | 15.5% | Coming soon | Coming soon |
| Gert Labs | 39.95% | Coming soon | Coming soon |

### Coding

- Winner: Not comparable
- GLM-4.7 public-lane score: 37.2 (Supported · #72/150)
- Kimi K2 public-lane score: Coming soon

| Benchmark | GLM-4.7 | Kimi K2 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 73.8% | 65.8% | GLM-4.7 |
| LiveCodeBench v6 | 84.9% | 53.7% | GLM-4.7 |
| SWE-Rebench | 58.7% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 41.0% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 82.2% | Coming soon | Coming soon |
| SWE-bench (Vals) | 69.4% | Coming soon | Coming soon |
| SWE Multilingual | Coming soon | 47.3% | Coming soon |

### Reasoning

- Winner: Not comparable
- GLM-4.7 public-lane score: 74.6 (Unranked · 2 rankable rows)
- Kimi K2 public-lane score: 62.3 (Unranked · 2 rankable rows)

### Knowledge

- Winner: Directional only
- GLM-4.7 public-lane score: 44.1 (Supported · #100/184)
- Kimi K2 public-lane score: 36.1 (Estimated · #129/184)

| Benchmark | GLM-4.7 | Kimi K2 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 85.7% | 75.1% | GLM-4.7 |
| MMLU-Pro | 84.3% | 81.1% | GLM-4.7 |
| HLE | 24.8% | 4.7% | GLM-4.7 |
| GPQA Diamond (Vals) | 80.1% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 82.7% | Coming soon | Coming soon |
| MMLU | Coming soon | 89.5% | Coming soon |
| SuperGPQA | Coming soon | 57.2% | Coming soon |
| SimpleQA | Coming soon | 31% | Coming soon |

### Instruction Following

- Winner: Directional only
- GLM-4.7 public-lane score: 82.8 (#54/148)
- Kimi K2 public-lane score: 48.4 (#96/148)

| Benchmark | GLM-4.7 | Kimi K2 | Winner |
|-----------|-----------|-----------|--------|
| IFEval | Coming soon | 89.8% | Coming soon |

### Mathematics

- Winner: Not comparable
- GLM-4.7 public-lane score: Coming soon
- Kimi K2 public-lane score: 0 (#12/12)

| Benchmark | GLM-4.7 | Kimi K2 | Winner |
|-----------|-----------|-----------|--------|
| AIME 2025 | 95.7% | 49.5% | GLM-4.7 |
| HMMT Feb 2025 | 97.1% | Coming soon | Coming soon |
| AIME 2024 | Coming soon | 69.6% | Coming soon |
| MATH-500 | Coming soon | 97.4% | Coming soon |

## FAQ

### Which is better overall, GLM-4.7 or Kimi K2?

GLM-4.7 has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between GLM-4.7 and Kimi K2?

The widest category gap is in instruction following, where the averages are 82.8 for GLM-4.7 and 48.4 for Kimi K2.

### How many benchmarks does GLM-4.7 cover on BenchLM?

GLM-4.7 currently has 17 sourced benchmark scores on BenchLM.

### How many benchmarks does Kimi K2 cover on BenchLM?

Kimi K2 currently has 13 sourced benchmark scores on BenchLM.

## Related Comparisons

- [GLM-4.7 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-glm-4-7)
- [Kimi K2 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-kimi-k2)
- [GLM-4.7 vs GPT-6.1 Sol](/compare/glm-4-7-vs-gpt-6-1-sol)
- [Kimi K2 vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-kimi-k2)

## Explore More

- [GLM-4.7 profile](/models/glm-4-7)
- [Kimi K2 profile](/models/kimi-k2)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)