Model comparison
Gemini 2.5 Flash vs GLM-4.5
GLM-4.5 is the stronger model overall, scoring 42.0 to 39.3 on the Noometry Index.
Last verified . 26 shared benchmarks.
GoogleSummary
- They share 26 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 4 categories and GLM-4.5 in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.5 leads 28.6 to 18.1.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 28.7% for Gemini 2.5 Flash and 54.2% for GLM-4.5.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $0.60 / $2.20 for GLM-4.5.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 131K.
- GLM-4.5 has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash | GLM-4.5 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 39.3 | 42.0 |
| Released | 2025-04-17 | 2025-07-27 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 66K | 98K |
| Input $ / M tokens | $0.30 | $0.60 |
| Output $ / M tokens | $2.50 | $2.20 |
| Results tracked | 54 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5 leads
Gemini 2.5 Flash: 35.8 (#220), GLM-4.5: 41.4 (#125)
| Benchmark | Gemini 2.5 Flash | GLM-4.5 |
|---|---|---|
| SWE-bench Verified (bash only) | 28.7% | 54.2% |
| WeirdML | 41.9% | 40.6% |
| LMArena Coding | 1424 | 1434 |
| ALE-Bench | 661.88 | 344.82 |
| Aider Polyglot | 55.1% | — |
| AlgoTune | — | 1.52 |
Agentic & Tool Use Not comparable
Gemini 2.5 Flash: 30.8 (#74), GLM-4.5: —
| Benchmark | Gemini 2.5 Flash | GLM-4.5 |
|---|---|---|
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning GLM-4.5 leads
Gemini 2.5 Flash: 18.1 (#286), GLM-4.5: 28.6 (#100)
| Benchmark | Gemini 2.5 Flash | GLM-4.5 |
|---|---|---|
| Kagi LLM Benchmark | 56.8% | 57.9% |
| LMArena Hard Prompts | 1422 | 1429 |
| ARC-AGI-2 | 2.5% | — |
| SimpleBench | 41.2% | — |
| ARC-AGI-1 | 33.3% | — |
| CritPt | 1.1% | — |
| EnigmaEval | 2.7% | — |
| DTBench | 76.5% | — |
| LMCA | 27.5% | — |
| Epoch Capabilities Index | 143.03 | — |
| ForecastBench | 60.6 | — |
Math Too close to call
Gemini 2.5 Flash: 39.9 (#98), GLM-4.5: 39.0 (#116)
| Benchmark | Gemini 2.5 Flash | GLM-4.5 |
|---|---|---|
| LMArena Math | 1415 | 1427 |
| OTIS Mock AIME 2024-2025 | 73.1% | — |
| Omni-MATH | 38.5% | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Too close to call
Gemini 2.5 Flash: 36.4 (#168), GLM-4.5: 35.9 (#179)
| Benchmark | Gemini 2.5 Flash | GLM-4.5 |
|---|---|---|
| Humanity's Last Exam | 12.1% | 8.3% |
| Confabulations | 16.8% | 11.3% |
| LMArena Expert | 1426 | 1433 |
| MMLU-Pro | 63.9% | — |
| Vectara Hallucination Rate | 7.8% | — |
| GPQA (HELM) | 39% | — |
Multimodal Not comparable
Gemini 2.5 Flash: 41.8 (#32), GLM-4.5: —
| Benchmark | Gemini 2.5 Flash | GLM-4.5 |
|---|---|---|
| LMArena Vision | 1253 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Too close to call
Gemini 2.5 Flash: 52.3 (#88), GLM-4.5: 52.8 (#77)
| Benchmark | Gemini 2.5 Flash | GLM-4.5 |
|---|---|---|
| LMArena Non-English | 1409 | 1417 |
| LMArena Chinese | 1450 | 1465 |
| LMArena French | 1433 | 1418 |
| LMArena German | 1418 | 1407 |
| LMArena Japanese | 1405 | 1415 |
| LMArena Korean | 1385 | 1380 |
| LMArena Russian | 1415 | 1414 |
| LMArena Spanish | 1421 | 1454 |
Instruction Following Gemini 2.5 Flash leads
Gemini 2.5 Flash: 75.7 (#54), GLM-4.5: 74.1 (#104)
| Benchmark | Gemini 2.5 Flash | GLM-4.5 |
|---|---|---|
| LMArena Instruction Following | 1405 | 1404 |
| IFEval | 89.8% | — |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#17), GLM-4.5: 38.2 (#201)
| Benchmark | Gemini 2.5 Flash | GLM-4.5 |
|---|---|---|
| Fiction.LiveBench | 77.8% | 58.3% |
| LMArena Longer Query | 1419 | 1412 |
Writing & Preference GLM-4.5 leads
Gemini 2.5 Flash: 53.8 (#157), GLM-4.5: 57.5 (#127)
| Benchmark | Gemini 2.5 Flash | GLM-4.5 |
|---|---|---|
| LMArena Text | 1417 | 1430 |
| LMArena Creative Writing | 1400 | 1395 |
| Short-Story Creative Writing | 76.5% | 73.4% |
| EQ-Bench Creative Writing | 1137 | 1343 |
| LMArena Multi-Turn | 1408 | 1415 |
| WildBench | 81.7% | — |
Frequently asked questions
Is Gemini 2.5 Flash better than GLM-4.5?
GLM-4.5 is the stronger model overall, scoring 42.0 to 39.3 on the Noometry Index.
Which is cheaper, Gemini 2.5 Flash or GLM-4.5?
Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; GLM-4.5 lists at $0.60 and $2.20.
Is Gemini 2.5 Flash or GLM-4.5 better for coding?
GLM-4.5 scores higher on coding benchmarks: 41.4 versus 35.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 131K.
How many benchmarks do Gemini 2.5 Flash and GLM-4.5 share?
26 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and GLM-4.5 has 27.