Model comparison
Gemini 1.5 Pro (May 2024) vs GLM-5.3-Flash
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 32.1 on the Noometry Index.
Last verified . 22 shared benchmarks.
GoogleSummary
- They share 22 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 0 categories and GLM-5.3-Flash in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.3-Flash leads 48.0 to 12.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 23.1% for Gemini 1.5 Pro (May 2024) and 93.9% for GLM-5.3-Flash.
- GLM-5.3-Flash has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | GLM-5.3-Flash | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 32.1 | 51.8 |
| Released | 2024-02-15 | 2026-08-20 |
| Weights | Proprietary | Open |
| Context window | — | 1M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.50 |
| Results tracked | 45 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3-Flash leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), GLM-5.3-Flash: 53.1 (#31)
| Benchmark | Gemini 1.5 Pro (May 2024) | GLM-5.3-Flash |
|---|---|---|
| LMArena Coding | 1294 | 1508 |
| DeepSWE | — | 63.4% |
| FrontierCode | — | 31.8% |
| CursorBench | — | 36.8% |
| LMArena WebDev | — | 1609 |
| FrontierSWE | — | 18.1% |
| SciCode | — | 51.6% |
| WeirdML | 22.2% | — |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| ALE-Bench | — | 303.55 |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use GLM-5.3-Flash leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), GLM-5.3-Flash: 34.2 (#47)
| Benchmark | Gemini 1.5 Pro (May 2024) | GLM-5.3-Flash |
|---|---|---|
| APEX-Agents | — | 52.8% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
| GDP.pdf | — | 14% |
Reasoning GLM-5.3-Flash leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), GLM-5.3-Flash: 48.0 (#42)
| Benchmark | Gemini 1.5 Pro (May 2024) | GLM-5.3-Flash |
|---|---|---|
| ARC-AGI-2 | 0.8% | 65.8% |
| LMArena Hard Prompts | 1296 | 1491 |
| Epoch Capabilities Index | 131.73 | 151.88 |
| SimpleBench | 27.1% | — |
| ARC-AGI-1 | — | 91% |
| CritPt | — | 15.4% |
| Chess Puzzles | — | 14% |
| Mystery Game Puzzles | — | 8% |
| DTBench | 59% | — |
| Surface Evolver Bench | — | 52.5% |
| Bench to the Future 3 | — | 0.15 |
| BIG-Bench Hard | 89.2% | — |
| ForecastBench | 58.4 | — |
Math GLM-5.3-Flash leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), GLM-5.3-Flash: 53.3 (#47)
| Benchmark | Gemini 1.5 Pro (May 2024) | GLM-5.3-Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 93.9% |
| LMArena Math | 1315 | 1500 |
| FrontierMath (Tiers 1-3) | — | 55.8% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 21% |
| Omni-MATH | 36.4% | — |
| MATH Level 5 | 70.4% | — |
Knowledge GLM-5.3-Flash leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), GLM-5.3-Flash: 58.4 (#36)
| Benchmark | Gemini 1.5 Pro (May 2024) | GLM-5.3-Flash |
|---|---|---|
| GPQA Diamond | 57.2% | 90.2% |
| LMArena Expert | 1279 | 1513 |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| GPQA (HELM) | 53.4% | — |
| MMLU | 86.9% | — |
Multimodal GLM-5.3-Flash leads
Gemini 1.5 Pro (May 2024): 36.8 (#77), GLM-5.3-Flash: 42.8 (#27)
| Benchmark | Gemini 1.5 Pro (May 2024) | GLM-5.3-Flash |
|---|---|---|
| LMArena Vision | 1161 | 1296 |
| Video-MME | 75% | — |
Multilingual GLM-5.3-Flash leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), GLM-5.3-Flash: 56.0 (#25)
| Benchmark | Gemini 1.5 Pro (May 2024) | GLM-5.3-Flash |
|---|---|---|
| LMArena Non-English | 1312 | 1462 |
| LMArena Chinese | 1331 | 1527 |
| LMArena French | 1302 | 1496 |
| LMArena German | 1286 | 1470 |
| LMArena Japanese | 1292 | 1429 |
| LMArena Korean | 1298 | 1446 |
| LMArena Russian | 1320 | 1469 |
| LMArena Spanish | 1311 | 1471 |
Instruction Following GLM-5.3-Flash leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), GLM-5.3-Flash: 77.5 (#20)
| Benchmark | Gemini 1.5 Pro (May 2024) | GLM-5.3-Flash |
|---|---|---|
| LMArena Instruction Following | 1297 | 1478 |
| IFEval | 83.7% | — |
Long Context GLM-5.3-Flash leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), GLM-5.3-Flash: 45.4 (#39)
| Benchmark | Gemini 1.5 Pro (May 2024) | GLM-5.3-Flash |
|---|---|---|
| LMArena Longer Query | 1308 | 1482 |
Writing & Preference GLM-5.3-Flash leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), GLM-5.3-Flash: 65.3 (#50)
| Benchmark | Gemini 1.5 Pro (May 2024) | GLM-5.3-Flash |
|---|---|---|
| LMArena Text | 1319 | 1471 |
| LMArena Creative Writing | 1333 | 1442 |
| LMArena Multi-Turn | 1296 | 1467 |
| WildBench | 81.3% | — |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than GLM-5.3-Flash?
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or GLM-5.3-Flash better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and GLM-5.3-Flash share?
22 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and GLM-5.3-Flash has 40.