Model comparison
Gemini 1.5 Pro (May 2024) vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 32.1 on the Noometry Index.
Last verified . 32 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 32 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 0 categories and Qwen3 235B-A22B in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 50.4 to 25.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 23.1% for Gemini 1.5 Pro (May 2024) and 86.7% for Qwen3 235B-A22B.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 32.1 | 43.5 |
| Released | 2024-02-15 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 45 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 235B-A22B |
|---|---|---|
| WeirdML | 22.2% | 41% |
| LMArena Coding | 1294 | 1445 |
| Aider Polyglot | — | 59.6% |
| SciCode | — | 42.4% |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Qwen3 235B-A22B leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
| Vending-Bench 2 | — | -11.34 |
Reasoning Qwen3 235B-A22B leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 235B-A22B |
|---|---|---|
| ARC-AGI-2 | 0.8% | 1.3% |
| SimpleBench | 27.1% | 31% |
| LMArena Hard Prompts | 1296 | 1433 |
| DTBench | 59% | 80.3% |
| Epoch Capabilities Index | 131.73 | 143.85 |
| ForecastBench | 58.4 | 59.7 |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 9% |
| LMCA | — | 29.3% |
| BIG-Bench Hard | 89.2% | — |
Math Qwen3 235B-A22B leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 86.7% |
| Omni-MATH | 36.4% | 71.8% |
| LMArena Math | 1315 | 1432 |
| MATH Level 5 | 70.4% | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3 235B-A22B leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 57.2% | 80.1% |
| MMLU-Pro | 73.7% | 84.4% |
| Confabulations | 13.5% | 15.6% |
| GPQA (HELM) | 53.4% | 72.7% |
| LMArena Expert | 1279 | 1463 |
| Humanity's Last Exam | 4.6% | — |
| SimpleQA Verified | — | 40.4% |
| Vectara Hallucination Rate | — | 9.3% |
| MMLU | 86.9% | — |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), Qwen3 235B-A22B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 235B-A22B |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Qwen3 235B-A22B leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1312 | 1409 |
| LMArena Chinese | 1331 | 1481 |
| LMArena French | 1302 | 1445 |
| LMArena German | 1286 | 1433 |
| LMArena Japanese | 1292 | 1399 |
| LMArena Korean | 1298 | 1391 |
| LMArena Russian | 1320 | 1411 |
| LMArena Spanish | 1311 | 1430 |
Instruction Following Qwen3 235B-A22B leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 235B-A22B |
|---|---|---|
| IFEval | 83.7% | 83.5% |
| LMArena Instruction Following | 1297 | 1408 |
Long Context Qwen3 235B-A22B leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1308 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Qwen3 235B-A22B leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1319 | 1419 |
| LMArena Creative Writing | 1333 | 1384 |
| WildBench | 81.3% | 86.6% |
| LMArena Multi-Turn | 1296 | 1432 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1366 |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Qwen3 235B-A22B share?
32 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Qwen3 235B-A22B has 49.