Model comparison
Gemini 2.5 Flash vs GLM-5.3-Flash
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 39.3 on the Noometry Index.
Last verified . 24 shared benchmarks.
GoogleSummary
- They share 24 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 1 category and GLM-5.3-Flash in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.3-Flash leads 48.0 to 18.1.
- The biggest single-benchmark swing is ARC-AGI-2: 2.5% for Gemini 2.5 Flash and 65.8% for GLM-5.3-Flash.
- GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $0.30 / $2.50 for Gemini 2.5 Flash.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 1M.
- GLM-5.3-Flash has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash | GLM-5.3-Flash | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 39.3 | 51.8 |
| Released | 2025-04-17 | 2026-08-20 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 1M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.30 | $0.15 |
| Output $ / M tokens | $2.50 | $0.50 |
| Results tracked | 54 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3-Flash leads
Gemini 2.5 Flash: 35.8 (#220), GLM-5.3-Flash: 53.1 (#31)
| Benchmark | Gemini 2.5 Flash | GLM-5.3-Flash |
|---|---|---|
| LMArena Coding | 1424 | 1508 |
| ALE-Bench | 661.88 | 303.55 |
| DeepSWE | — | 63.4% |
| FrontierCode | — | 31.8% |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| CursorBench | — | 36.8% |
| LMArena WebDev | — | 1609 |
| FrontierSWE | — | 18.1% |
| SciCode | — | 51.6% |
| WeirdML | 41.9% | — |
Agentic & Tool Use GLM-5.3-Flash leads
Gemini 2.5 Flash: 30.8 (#74), GLM-5.3-Flash: 34.2 (#47)
| Benchmark | Gemini 2.5 Flash | GLM-5.3-Flash |
|---|---|---|
| Terminal-Bench | 17.1% | — |
| APEX-Agents | — | 52.8% |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| GDP.pdf | — | 14% |
| Vending-Bench 2 | 548.84 | — |
Reasoning GLM-5.3-Flash leads
Gemini 2.5 Flash: 18.1 (#286), GLM-5.3-Flash: 48.0 (#42)
| Benchmark | Gemini 2.5 Flash | GLM-5.3-Flash |
|---|---|---|
| ARC-AGI-2 | 2.5% | 65.8% |
| ARC-AGI-1 | 33.3% | 91% |
| CritPt | 1.1% | 15.4% |
| LMArena Hard Prompts | 1422 | 1491 |
| Epoch Capabilities Index | 143.03 | 151.88 |
| SimpleBench | 41.2% | — |
| Kagi LLM Benchmark | 56.8% | — |
| Chess Puzzles | — | 14% |
| EnigmaEval | 2.7% | — |
| Mystery Game Puzzles | — | 8% |
| DTBench | 76.5% | — |
| LMCA | 27.5% | — |
| Surface Evolver Bench | — | 52.5% |
| Bench to the Future 3 | — | 0.15 |
| ForecastBench | 60.6 | — |
Math GLM-5.3-Flash leads
Gemini 2.5 Flash: 39.9 (#98), GLM-5.3-Flash: 53.3 (#47)
| Benchmark | Gemini 2.5 Flash | GLM-5.3-Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 93.9% |
| LMArena Math | 1415 | 1500 |
| FrontierMath (Tiers 1-3) | — | 55.8% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 21% |
| Omni-MATH | 38.5% | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge GLM-5.3-Flash leads
Gemini 2.5 Flash: 36.4 (#168), GLM-5.3-Flash: 58.4 (#36)
| Benchmark | Gemini 2.5 Flash | GLM-5.3-Flash |
|---|---|---|
| LMArena Expert | 1426 | 1513 |
| GPQA Diamond | — | 90.2% |
| Humanity's Last Exam | 12.1% | — |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| Vectara Hallucination Rate | 7.8% | — |
| GPQA (HELM) | 39% | — |
Multimodal GLM-5.3-Flash leads
Gemini 2.5 Flash: 41.8 (#32), GLM-5.3-Flash: 42.8 (#27)
| Benchmark | Gemini 2.5 Flash | GLM-5.3-Flash |
|---|---|---|
| LMArena Vision | 1253 | 1296 |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual GLM-5.3-Flash leads
Gemini 2.5 Flash: 52.3 (#88), GLM-5.3-Flash: 56.0 (#25)
| Benchmark | Gemini 2.5 Flash | GLM-5.3-Flash |
|---|---|---|
| LMArena Non-English | 1409 | 1462 |
| LMArena Chinese | 1450 | 1527 |
| LMArena French | 1433 | 1496 |
| LMArena German | 1418 | 1470 |
| LMArena Japanese | 1405 | 1429 |
| LMArena Korean | 1385 | 1446 |
| LMArena Russian | 1415 | 1469 |
| LMArena Spanish | 1421 | 1471 |
Instruction Following GLM-5.3-Flash leads
Gemini 2.5 Flash: 75.7 (#54), GLM-5.3-Flash: 77.5 (#20)
| Benchmark | Gemini 2.5 Flash | GLM-5.3-Flash |
|---|---|---|
| LMArena Instruction Following | 1405 | 1478 |
| IFEval | 89.8% | — |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#17), GLM-5.3-Flash: 45.4 (#39)
| Benchmark | Gemini 2.5 Flash | GLM-5.3-Flash |
|---|---|---|
| LMArena Longer Query | 1419 | 1482 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference GLM-5.3-Flash leads
Gemini 2.5 Flash: 53.8 (#157), GLM-5.3-Flash: 65.3 (#50)
| Benchmark | Gemini 2.5 Flash | GLM-5.3-Flash |
|---|---|---|
| LMArena Text | 1417 | 1471 |
| LMArena Creative Writing | 1400 | 1442 |
| LMArena Multi-Turn | 1408 | 1467 |
| Short-Story Creative Writing | 76.5% | — |
| EQ-Bench Creative Writing | 1137 | — |
| WildBench | 81.7% | — |
Frequently asked questions
Is Gemini 2.5 Flash better than GLM-5.3-Flash?
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 39.3 on the Noometry Index.
Which is cheaper, Gemini 2.5 Flash or GLM-5.3-Flash?
GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; Gemini 2.5 Flash lists at $0.30 and $2.50.
Is Gemini 2.5 Flash or GLM-5.3-Flash better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 35.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 1M.
How many benchmarks do Gemini 2.5 Flash and GLM-5.3-Flash share?
24 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and GLM-5.3-Flash has 40.