# Gemini 3 Deep Think vs GLM-4.5-Air

> GLM-4.5-Air has enough public results to be ranked (#177); Gemini 3 Deep Think does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/gemini-3-deep-think-vs-glm-4-5-air
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where Gemini 3 Deep Think leads 70.2 to 24.1.
- GLM-4.5-Air has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3 Deep Think | GLM-4.5-Air |
|---|---|---|
| Provider | Google | Z.ai (Zhipu) |
| Noometry Index | 58.3 | 38.9 |
| Rank | — | 177 |
| Context | — | 131K |
| Input $/M | — | $0.20 |
| Output $/M | — | $1.10 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3 Deep Think: —
- GLM-4.5-Air: 33.3 (#259)

| Benchmark | Gemini 3 Deep Think | GLM-4.5-Air |
|---|---|---|
| GSO | — | 2.9% |
| LMArena Coding | — | 1397 |

## Reasoning

- Gemini 3 Deep Think: 70.2 (#14)
- GLM-4.5-Air: 24.1 (#166)

| Benchmark | Gemini 3 Deep Think | GLM-4.5-Air |
|---|---|---|
| ARC-AGI-2 | 84.6% | — |
| Kagi LLM Benchmark | — | 43% |
| ARC-AGI-1 | 96% | — |
| CritPt | 25.7% | — |
| LMArena Hard Prompts | — | 1379 |
| ForecastBench | — | 59.2 |

## Math

- Gemini 3 Deep Think: —
- GLM-4.5-Air: 36.2 (#170)

| Benchmark | Gemini 3 Deep Think | GLM-4.5-Air |
|---|---|---|
| Omni-MATH | — | 39.1% |
| LMArena Math | — | 1396 |

## Knowledge

- Gemini 3 Deep Think: —
- GLM-4.5-Air: 35.0 (#191)

| Benchmark | Gemini 3 Deep Think | GLM-4.5-Air |
|---|---|---|
| Humanity's Last Exam | — | 8.1% |
| MMLU-Pro | — | 76.2% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 59.4% |
| LMArena Expert | — | 1370 |

## Multilingual

- Gemini 3 Deep Think: —
- GLM-4.5-Air: 49.1 (#135)

| Benchmark | Gemini 3 Deep Think | GLM-4.5-Air |
|---|---|---|
| LMArena Non-English | — | 1366 |
| LMArena Chinese | — | 1426 |
| LMArena French | — | 1399 |
| LMArena German | — | 1377 |
| LMArena Japanese | — | 1348 |
| LMArena Korean | — | 1308 |
| LMArena Russian | — | 1373 |
| LMArena Spanish | — | 1386 |

## Instruction Following

- Gemini 3 Deep Think: —
- GLM-4.5-Air: 69.6 (#171)

| Benchmark | Gemini 3 Deep Think | GLM-4.5-Air |
|---|---|---|
| IFEval | — | 81.2% |
| LMArena Instruction Following | — | 1354 |

## Long Context

- Gemini 3 Deep Think: —
- GLM-4.5-Air: 41.6 (#135)

| Benchmark | Gemini 3 Deep Think | GLM-4.5-Air |
|---|---|---|
| LMArena Longer Query | — | 1366 |

## Writing & Preference

- Gemini 3 Deep Think: —
- GLM-4.5-Air: 55.9 (#139)

| Benchmark | Gemini 3 Deep Think | GLM-4.5-Air |
|---|---|---|
| LMArena Text | — | 1384 |
| LMArena Creative Writing | — | 1343 |
| WildBench | — | 78.9% |
| LMArena Multi-Turn | — | 1371 |

## FAQ

### Is Gemini 3 Deep Think better than GLM-4.5-Air?

GLM-4.5-Air has enough public results to be ranked (#177); Gemini 3 Deep Think does not yet, so treat this comparison as directional.

### How many benchmarks do Gemini 3 Deep Think and GLM-4.5-Air share?

0 benchmarks have published results for both models. Gemini 3 Deep Think has 3 scored results on Noometry and GLM-4.5-Air has 27.