Model comparison
Gemini 1.5 Flash (May 2024) vs GLM-5
GLM-5 is the stronger model overall, scoring 45.9 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-5 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5 leads 52.2 to 26.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.3% for Gemini 1.5 Flash (May 2024) and 80% for GLM-5.
- GLM-5 has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Flash (May 2024) | GLM-5 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 32.9 | 45.9 |
| Released | 2024-05-14 | 2026-02-11 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $3.20 |
| Results tracked | 42 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
Gemini 1.5 Flash (May 2024): 33.9 (#233), GLM-5: 49.0 (#47)
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-5 |
|---|---|---|
| WeirdML | 24.9% | 48.2% |
| LMArena Coding | 1262 | 1461 |
| SWE-bench Verified | — | 72.1% |
| SWE-bench Verified (bash only) | — | 72.8% |
| LMArena WebDev | — | 1434 |
| SWE-bench Multilingual | — | 69.7% |
| BigCodeBench Instruct | 43.5% | — |
| BigCodeBench Complete | 55.1% | — |
| ALE-Bench | — | 765.62 |
| HumanEval+ | 75.6% | — |
| MBPP+ | 67.5% | — |
Agentic & Tool Use GLM-5 leads
Gemini 1.5 Flash (May 2024): 26.3 (#97), GLM-5: 30.9 (#65)
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-5 |
|---|---|---|
| Terminal-Bench | — | 52.4% |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 73.7% |
| τ²-bench Telecom | — | 86.8% |
| BALROG | 14.6% | — |
| Vending-Bench 2 | — | 4,432 |
Reasoning GLM-5 leads
Gemini 1.5 Flash (May 2024): 20.8 (#212), GLM-5: 27.6 (#100)
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-5 |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1451 |
| Epoch Capabilities Index | 129.37 | 145.84 |
| ForecastBench | 53.9 | 61 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | — | 53.2% |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 74.8% |
| ARC-AGI-1 | — | 44.7% |
| Chess Puzzles | — | 10% |
| DTBench | 53.8% | — |
| PIQA | 87.5% | — |
Math GLM-5 leads
Gemini 1.5 Flash (May 2024): 20.8 (#274), GLM-5: 44.8 (#66)
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.3% | 80% |
| LMArena Math | 1269 | 1440 |
| FrontierMath (Feb 2025 set) | 0% | 16.4% |
| MathArena Final-Answer Competitions | — | 65.7% |
| Omni-MATH | 30.4% | — |
| MATH Level 5 | 61.9% | — |
| FrontierMath Tier 4 (v1) | — | 2.1% |
| GSM8K | 82.4% | — |
Knowledge GLM-5 leads
Gemini 1.5 Flash (May 2024): 26.2 (#253), GLM-5: 52.2 (#59)
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-5 |
|---|---|---|
| GPQA Diamond | 47.3% | 87.8% |
| LMArena Expert | 1233 | 1454 |
| MMLU-Pro | 67.8% | — |
| Vectara Hallucination Rate | — | 10.1% |
| GPQA (HELM) | 43.7% | — |
| BoolQ | 85.8% | — |
| MMLU | 77.9% | — |
Multimodal Not comparable
Gemini 1.5 Flash (May 2024): 35.3 (#76), GLM-5: —
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-5 |
|---|---|---|
| LMArena Vision | 1141 | — |
| Video-MME | 70.3% | — |
| GeoBench | 76% | — |
Multilingual GLM-5 leads
Gemini 1.5 Flash (May 2024): 43.1 (#184), GLM-5: 53.9 (#57)
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-5 |
|---|---|---|
| LMArena Non-English | 1278 | 1430 |
| LMArena Chinese | 1295 | 1511 |
| LMArena French | 1257 | 1455 |
| LMArena German | 1262 | 1445 |
| LMArena Japanese | 1252 | 1416 |
| LMArena Korean | 1220 | 1421 |
| LMArena Russian | 1288 | 1436 |
| LMArena Spanish | 1242 | 1452 |
Instruction Following GLM-5 leads
Gemini 1.5 Flash (May 2024): 67.0 (#199), GLM-5: 75.4 (#64)
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-5 |
|---|---|---|
| LMArena Instruction Following | 1258 | 1427 |
| IFEval | 83.1% | — |
Long Context GLM-5 leads
Gemini 1.5 Flash (May 2024): 39.0 (#182), GLM-5: 44.6 (#58)
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-5 |
|---|---|---|
| LMArena Longer Query | 1284 | 1446 |
| CL-bench | — | 18.7% |
Writing & Preference GLM-5 leads
Gemini 1.5 Flash (May 2024): 48.9 (#190), GLM-5: 66.2 (#38)
| Benchmark | Gemini 1.5 Flash (May 2024) | GLM-5 |
|---|---|---|
| LMArena Text | 1287 | 1446 |
| LMArena Creative Writing | 1285 | 1438 |
| LMArena Multi-Turn | 1253 | 1456 |
| EQ-Bench Creative Writing | — | 1601 |
| WildBench | 79.2% | — |
Frequently asked questions
Is Gemini 1.5 Flash (May 2024) better than GLM-5?
GLM-5 is the stronger model overall, scoring 45.9 to 32.9 on the Noometry Index.
Is Gemini 1.5 Flash (May 2024) or GLM-5 better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 33.9 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Flash (May 2024) and GLM-5 share?
23 benchmarks have published results for both models. Gemini 1.5 Flash (May 2024) has 42 scored results on Noometry and GLM-5 has 45.