Model comparison
Gemini 1.5 Flash (May 2024) vs GLM-4.5-Air
GLM-4.5-Air is the stronger model overall, scoring 38.7 to 32.9 on the Noometry Index.
Last verified . 23 shared benchmarks.
GoogleSummary
- They share 23 benchmarks with published results for both. Gemini 1.5 Flash (May 2024) scores higher in 0 categories and GLM-4.5-Air in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.5-Air leads 33.8 to 20.8.
- The biggest single-benchmark swing is GPQA (HELM): 43.7% for Gemini 1.5 Flash (May 2024) and 59.4% for GLM-4.5-Air.
- GLM-4.5-Air has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Flash (May 2024) | GLM-4.5-Air | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 32.9 | 38.7 |
| Released | 2024-05-14 | 2025-07-20 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 98K |
| Input $ / M tokens | — | $0.20 |
| Output $ / M tokens | — | $1.10 |
| Results tracked | 42 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 1.5 Flash (May 2024): 33.9 (#233), GLM-4.5-Air: 34.5 (#225)
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-4.5-Air |
|---|---|---|
| LMArena Coding | 1262 | 1397 |
| GSO | — | 2.9% |
| WeirdML | 24.9% | — |
| BigCodeBench Instruct | 43.5% | — |
| BigCodeBench Complete | 55.1% | — |
| HumanEval+ | 75.6% | — |
| MBPP+ | 67.5% | — |
Agentic & Tool Use Not comparable
Gemini 1.5 Flash (May 2024): 26.3 (#97), GLM-4.5-Air: —
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-4.5-Air |
|---|---|---|
| BALROG | 14.6% | — |
Reasoning GLM-4.5-Air leads
Gemini 1.5 Flash (May 2024): 20.8 (#212), GLM-4.5-Air: 23.3 (#166)
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-4.5-Air |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1379 |
| ForecastBench | 53.9 | 59.2 |
| Kagi LLM Benchmark | — | 43% |
| DTBench | 53.8% | — |
| Epoch Capabilities Index | 129.37 | — |
| PIQA | 87.5% | — |
Math GLM-4.5-Air leads
Gemini 1.5 Flash (May 2024): 20.8 (#274), GLM-4.5-Air: 33.8 (#166)
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-4.5-Air |
|---|---|---|
| Omni-MATH | 30.4% | 39.1% |
| LMArena Math | 1269 | 1396 |
| OTIS Mock AIME 2024-2025 | 16.3% | — |
| MATH Level 5 | 61.9% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
| GSM8K | 82.4% | — |
Knowledge GLM-4.5-Air leads
Gemini 1.5 Flash (May 2024): 26.2 (#253), GLM-4.5-Air: 34.6 (#184)
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-4.5-Air |
|---|---|---|
| MMLU-Pro | 67.8% | 76.2% |
| GPQA (HELM) | 43.7% | 59.4% |
| LMArena Expert | 1233 | 1370 |
| GPQA Diamond | 47.3% | — |
| Humanity's Last Exam | — | 8.1% |
| Vectara Hallucination Rate | — | 9.3% |
| BoolQ | 85.8% | — |
| MMLU | 77.9% | — |
Multimodal Not comparable
Gemini 1.5 Flash (May 2024): 35.3 (#76), GLM-4.5-Air: —
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-4.5-Air |
|---|---|---|
| LMArena Vision | 1141 | — |
| Video-MME | 70.3% | — |
| GeoBench | 76% | — |
Multilingual GLM-4.5-Air leads
Gemini 1.5 Flash (May 2024): 43.1 (#184), GLM-4.5-Air: 49.4 (#130)
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-4.5-Air |
|---|---|---|
| LMArena Non-English | 1278 | 1366 |
| LMArena Chinese | 1295 | 1427 |
| LMArena French | 1257 | 1399 |
| LMArena German | 1262 | 1376 |
| LMArena Japanese | 1252 | 1348 |
| LMArena Korean | 1220 | 1306 |
| LMArena Russian | 1288 | 1373 |
| LMArena Spanish | 1242 | 1385 |
Instruction Following GLM-4.5-Air leads
Gemini 1.5 Flash (May 2024): 67.0 (#199), GLM-4.5-Air: 69.8 (#165)
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-4.5-Air |
|---|---|---|
| IFEval | 83.1% | 81.2% |
| LMArena Instruction Following | 1258 | 1353 |
Long Context GLM-4.5-Air leads
Gemini 1.5 Flash (May 2024): 39.0 (#182), GLM-4.5-Air: 41.6 (#130)
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-4.5-Air |
|---|---|---|
| LMArena Longer Query | 1284 | 1367 |
Writing & Preference GLM-4.5-Air leads
Gemini 1.5 Flash (May 2024): 48.9 (#190), GLM-4.5-Air: 56.1 (#134)
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-4.5-Air |
|---|---|---|
| LMArena Text | 1287 | 1384 |
| LMArena Creative Writing | 1285 | 1343 |
| WildBench | 79.2% | 78.9% |
| LMArena Multi-Turn | 1253 | 1371 |
Frequently asked questions
Is Gemini 1.5 Flash (May 2024) better than GLM-4.5-Air?
GLM-4.5-Air is the stronger model overall, scoring 38.7 to 32.9 on the Noometry Index.
Is Gemini 1.5 Flash (May 2024) or GLM-4.5-Air better for coding?
They score almost the same on coding (33.9 vs 34.5); test both on your own repository before choosing.
How many benchmarks do Gemini 1.5 Flash (May 2024) and GLM-4.5-Air share?
23 benchmarks have published results for both models. Gemini 1.5 Flash (May 2024) has 42 scored results on Noometry and GLM-4.5-Air has 27.