# GLM-4.7-Flash vs Kimi K3

> Kimi K3 is the stronger model overall, scoring 59.5 to 38.4 on the Noometry Index. GLM-4.7-Flash costs 41× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-4-7-flash-vs-kimi-k3
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. GLM-4.7-Flash scores higher in 0 categories and Kimi K3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K3 leads 63.0 to 20.2.
- The biggest single-benchmark swing is Chess Puzzles: 0% for GLM-4.7-Flash and 39% for Kimi K3.
- GLM-4.7-Flash is cheaper at $0.06 / $0.40 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 200K.

## Snapshot

| | GLM-4.7-Flash | Kimi K3 |
|---|---|---|
| Provider | Z.ai (Zhipu) | Moonshot AI |
| Noometry Index | 38.4 | 59.5 |
| Rank | 175 | 12 |
| Context | 200K | 1.05M |
| Input $/M | $0.06 | $3 |
| Output $/M | $0.40 | $15 |
| Weights | Open | Open |

## Coding

- GLM-4.7-Flash: 40.0 (#133)
- Kimi K3: 60.6 (#8)

| Benchmark | GLM-4.7-Flash | Kimi K3 |
|---|---|---|
| LMArena Coding | 1383 | 1509 |
| DeepSWE | — | 68.5% |
| FrontierCode | — | 44.2% |
| LMArena WebDev | — | 1659 |
| FrontierSWE | — | 25.9% |
| SciCode | — | 59.5% |
| WeirdML | — | 82.6% |
| ALE-Bench | — | 1,524 |

## Agentic & Tool Use

- GLM-4.7-Flash: —
- Kimi K3: 41.8 (#19)

| Benchmark | GLM-4.7-Flash | Kimi K3 |
|---|---|---|
| APEX-Agents | — | 50.6% |
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 32% |
| GBAEval | — | 48.3% |
| GDP.pdf | — | 19% |
| Vending-Bench 2 | — | 5,165 |

## Reasoning

- GLM-4.7-Flash: 20.2 (#224)
- Kimi K3: 63.0 (#15)

| Benchmark | GLM-4.7-Flash | Kimi K3 |
|---|---|---|
| Chess Puzzles | 0% | 39% |
| LMArena Hard Prompts | 1356 | 1495 |
| ARC-AGI-2 | — | 60.4% |
| SimpleBench | — | 60.7% |
| NYT Connections (extended) | — | 93.6% |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 23.4% |
| Mystery Game Puzzles | — | 26% |
| DTBench | — | 91.2% |
| LMCA | — | 52.7% |
| Surface Evolver Bench | — | 95% |
| Epoch Capabilities Index | — | 157.68 |
| ForecastBench | — | 61.1 |

## Math

- GLM-4.7-Flash: 34.4 (#159)
- Kimi K3: 74.0 (#13)

| Benchmark | GLM-4.7-Flash | Kimi K3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 58.3% | 97.2% |
| LMArena Math | 1354 | 1493 |
| FrontierMath (Tiers 1-3) | — | 72.2% |
| FrontierMath Tier 4 | — | 39% |
| MathArena Final-Answer Competitions | — | 87.8% |
| ProofBench | — | 87% |

## Knowledge

- GLM-4.7-Flash: 35.4 (#177)
- Kimi K3: 63.2 (#19)

| Benchmark | GLM-4.7-Flash | Kimi K3 |
|---|---|---|
| GPQA Diamond | 60.5% | 93.1% |
| LMArena Expert | 1357 | 1520 |
| SimpleQA Verified | — | 50.6% |
| Vectara Hallucination Rate | 9.3% | — |

## Multimodal

- GLM-4.7-Flash: —
- Kimi K3: 38.4 (#58)

| Benchmark | GLM-4.7-Flash | Kimi K3 |
|---|---|---|
| Blueprint-Bench 2 | — | 29.5% |
| Furniture Assembly | — | 34.2% |

## Multilingual

- GLM-4.7-Flash: 46.8 (#152)
- Kimi K3: 56.5 (#20)

| Benchmark | GLM-4.7-Flash | Kimi K3 |
|---|---|---|
| LMArena Non-English | 1331 | 1466 |
| LMArena Chinese | 1403 | 1528 |
| LMArena French | 1332 | 1488 |
| LMArena German | 1336 | 1474 |
| LMArena Korean | 1284 | 1465 |
| LMArena Russian | 1333 | 1481 |
| LMArena Spanish | 1351 | 1478 |
| LMArena Japanese | — | 1492 |

## Instruction Following

- GLM-4.7-Flash: 70.3 (#162)
- Kimi K3: 77.8 (#13)

| Benchmark | GLM-4.7-Flash | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | 1327 | 1481 |

## Long Context

- GLM-4.7-Flash: 40.9 (#143)
- Kimi K3: 45.8 (#27)

| Benchmark | GLM-4.7-Flash | Kimi K3 |
|---|---|---|
| LMArena Longer Query | 1345 | 1494 |

## Writing & Preference

- GLM-4.7-Flash: 47.7 (#206)
- Kimi K3: 76.7 (#4)

| Benchmark | GLM-4.7-Flash | Kimi K3 |
|---|---|---|
| LMArena Text | 1351 | 1476 |
| LMArena Creative Writing | 1297 | 1452 |
| EQ-Bench Creative Writing | 1125 | 2082 |
| LMArena Multi-Turn | 1342 | 1488 |
| EQ-Bench 4 | — | 1339 |

## FAQ

### Is GLM-4.7-Flash better than Kimi K3?

Kimi K3 is the stronger model overall, scoring 59.5 to 38.4 on the Noometry Index. GLM-4.7-Flash costs 41× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.

### Which is cheaper, GLM-4.7-Flash or Kimi K3?

GLM-4.7-Flash is cheaper. It lists at $0.06 per million input tokens and $0.40 per million output tokens; Kimi K3 lists at $3 and $15.

### Is GLM-4.7-Flash or Kimi K3 better for coding?

Kimi K3 scores higher on coding benchmarks: 60.6 versus 40.0 in the Noometry coding category.

### Which has the bigger context window?

Kimi K3 does, with 1.05M tokens against 200K.

### How many benchmarks do GLM-4.7-Flash and Kimi K3 share?

20 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and Kimi K3 has 53.