Model comparison
Gemini 3.8 Flash vs GLM-4.5-Air
Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 38.7 on the Noometry Index. GLM-4.5-Air costs 3.5× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
GoogleSummary
- They share 18 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 8 categories and GLM-4.5-Air in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 64.7 to 23.3.
- The biggest single-benchmark swing is Humanity's Last Exam: 44.5% for Gemini 3.8 Flash and 8.1% for GLM-4.5-Air.
- GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.8 Flash.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 131K.
- GLM-4.5-Air has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.8 Flash | GLM-4.5-Air | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 59.5 | 38.7 |
| Released | 2026-09-02 | 2025-07-20 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 66K | 98K |
| Input $ / M tokens | $0.75 | $0.20 |
| Output $ / M tokens | $3.75 | $1.10 |
| Results tracked | 46 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.8 Flash leads
Gemini 3.8 Flash: 56.4 (#17), GLM-4.5-Air: 34.5 (#225)
| Benchmark | Gemini 3.8 Flash | GLM-4.5-Air |
|---|---|---|
| LMArena Coding | 1512 | 1397 |
| DeepSWE | 73.8% | — |
| FrontierCode | 41.2% | — |
| CursorBench | 39.6% | — |
| LMArena WebDev | 1581 | — |
| FrontierSWE | 19.6% | — |
| SciCode | 56.6% | — |
| GSO | — | 2.9% |
| ALE-Bench | 1,270 | — |
Agentic & Tool Use Not comparable
Gemini 3.8 Flash: 40.3 (#22), GLM-4.5-Air: —
| Benchmark | Gemini 3.8 Flash | GLM-4.5-Air |
|---|---|---|
| APEX-Agents | 64.3% | — |
| GDP.pdf | 23.4% | — |
| Vending-Bench 2 | 5,094 | — |
Reasoning Gemini 3.8 Flash leads
Gemini 3.8 Flash: 64.7 (#13), GLM-4.5-Air: 23.3 (#166)
| Benchmark | Gemini 3.8 Flash | GLM-4.5-Air |
|---|---|---|
| LMArena Hard Prompts | 1506 | 1379 |
| Kagi LLM Benchmark | — | 43% |
| NYT Connections (extended) | 97.4% | — |
| CritPt | 18.3% | — |
| Chess Puzzles | 61% | — |
| Mystery Game Puzzles | 47% | — |
| DTBench | 95.7% | — |
| LMCA | 52.9% | — |
| Surface Evolver Bench | 76.9% | — |
| Epoch Capabilities Index | 157.13 | — |
| ForecastBench | — | 59.2 |
Math Gemini 3.8 Flash leads
Gemini 3.8 Flash: 65.2 (#22), GLM-4.5-Air: 33.8 (#166)
| Benchmark | Gemini 3.8 Flash | GLM-4.5-Air |
|---|---|---|
| LMArena Math | 1528 | 1396 |
| FrontierMath (Tiers 1-3) | 68.4% | — |
| FrontierMath Tier 4 | 22% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |
| ProofBench | 48% | — |
| Omni-MATH | — | 39.1% |
Knowledge Gemini 3.8 Flash leads
Gemini 3.8 Flash: 74.9 (#2), GLM-4.5-Air: 34.6 (#184)
| Benchmark | Gemini 3.8 Flash | GLM-4.5-Air |
|---|---|---|
| Humanity's Last Exam | 44.5% | 8.1% |
| LMArena Expert | 1529 | 1370 |
| GPQA Diamond | 95.4% | — |
| SimpleQA Verified | 69.7% | — |
| MMLU-Pro | — | 76.2% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 59.4% |
Multimodal Not comparable
Gemini 3.8 Flash: 40.9 (#33), GLM-4.5-Air: —
| Benchmark | Gemini 3.8 Flash | GLM-4.5-Air |
|---|---|---|
| LMArena Vision | 1312 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 31.7% | — |
Multilingual Gemini 3.8 Flash leads
Gemini 3.8 Flash: 57.9 (#5), GLM-4.5-Air: 49.4 (#130)
| Benchmark | Gemini 3.8 Flash | GLM-4.5-Air |
|---|---|---|
| LMArena Non-English | 1486 | 1366 |
| LMArena Chinese | 1547 | 1427 |
| LMArena French | 1502 | 1399 |
| LMArena German | 1470 | 1376 |
| LMArena Japanese | 1505 | 1348 |
| LMArena Korean | 1479 | 1306 |
| LMArena Russian | 1507 | 1373 |
| LMArena Spanish | 1492 | 1385 |
Instruction Following Gemini 3.8 Flash leads
Gemini 3.8 Flash: 78.2 (#11), GLM-4.5-Air: 69.8 (#165)
| Benchmark | Gemini 3.8 Flash | GLM-4.5-Air |
|---|---|---|
| LMArena Instruction Following | 1489 | 1353 |
| IFEval | — | 81.2% |
Long Context Gemini 3.8 Flash leads
Gemini 3.8 Flash: 46.2 (#23), GLM-4.5-Air: 41.6 (#130)
| Benchmark | Gemini 3.8 Flash | GLM-4.5-Air |
|---|---|---|
| LMArena Longer Query | 1506 | 1367 |
Writing & Preference Gemini 3.8 Flash leads
Gemini 3.8 Flash: 72.1 (#16), GLM-4.5-Air: 56.1 (#134)
| Benchmark | Gemini 3.8 Flash | GLM-4.5-Air |
|---|---|---|
| LMArena Text | 1494 | 1384 |
| LMArena Creative Writing | 1485 | 1343 |
| LMArena Multi-Turn | 1503 | 1371 |
| EQ-Bench Creative Writing | 1748 | — |
| WildBench | — | 78.9% |
Frequently asked questions
Is Gemini 3.8 Flash better than GLM-4.5-Air?
Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 38.7 on the Noometry Index. GLM-4.5-Air costs 3.5× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.8 Flash or GLM-4.5-Air?
GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; Gemini 3.8 Flash lists at $0.75 and $3.75.
Is Gemini 3.8 Flash or GLM-4.5-Air better for coding?
Gemini 3.8 Flash scores higher on coding benchmarks: 56.4 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.8 Flash does, with 1.05M tokens against 131K.
How many benchmarks do Gemini 3.8 Flash and GLM-4.5-Air share?
18 benchmarks have published results for both models. Gemini 3.8 Flash has 46 scored results on Noometry and GLM-4.5-Air has 27.