Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
MiMo-V2.6-Pro
Qwen3.8-Max
Kimi K3
GLM-5.3
GPT-5.5
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
Grok 4.20 Beta
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 PreviewQwen3.8-Max vs Gemini 3 Pro
- Qwen3.8-Max and Gemini 3 Pro are level on LMArena’s text leaderboard (1484 and 1480).
- On the 7 Vals AI benchmarks both have taken, Qwen3.8-Max wins 5 and Gemini 3 Pro wins 2 (Qwen3.8-Max: SWE-bench, Vibe Code Bench, LiveCodeBench).
LatestQwen3.8-Max 1484Gemini 3 Pro 1480
Side by side
Models (2/6)
- Qwen3.8-Max
- Gemini 3 Pro
| Benchmark | Qwen3.8-Max | Gemini 3 Pro |
|---|---|---|
| The model | ||
| Lab | Alibaba | |
| Released | 2026-09-03 | — |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Input, per 1M tokens | $2 | — |
| Output, per 1M tokens | $6 | — |
| LMArena, people’s votes | ||
| LMArena TextMillions of people compare two anonymous models side by side and vote for the better answer | 1484#15 of 351 | 1480#21 of 351 |
| LMArena WebDevPeople ask two anonymous models to build the same web app, try both and vote for the better one | 1673#12 of 124 | 1440#80 of 124 |
| LMArena VisionSide-by-side votes on prompts that include an image | 1313#10 of 146 | 1305#16 of 146 |
| LMArena CodingLMArena’s text votes on prompts that ask for code | 1503#21 of 346 | 1481#55 of 346 |
| LMArena MathLMArena’s text votes on math prompts | 1501#15 of 339 | 1476#38 of 339 |
| LMArena Creative writingLMArena’s text votes on stories, poems and other creative writing | 1477#16 of 349 | 1483#13 of 349 |
| LMArena Hard promptsLMArena’s text votes on the hardest prompts | 1497#16 of 351 | 1480#39 of 351 |
| LMArena Instruction followingLMArena’s text votes on prompts with specific instructions to follow | 1481#18 of 351 | 1458#43 of 351 |
| Vals AI, overall | ||
| Vals IndexVals AI’s headline score | 59.05%#11 of 27 | — |
| Vals AI, coding | ||
| Terminal-Bench 4.0Frontier-difficulty tasks an agent completes in a real terminal | 34.34%#18 of 55 | — |
| SWE-benchReal GitHub issues from open-source projects | 85.60%#16 of 85 | 76.40%#37 of 85 |
| Vibe Code BenchBuilding complete web apps from a plain-language brief, graded on whether the app works | 64.70%#49 of 115 | 14.30%#91 of 115 |
| Code MigrationRewriting working programs in a new language, graded on whether the new program still passes its tests | 57.19%#10 of 28 | — |
| LiveCodeBenchFresh competitive programming problems, collected after models’ training cut-offs to avoid contamination | 87.85%#10 of 143 | 86.41%#23 of 143 |
| Vals AI, finance | ||
| Finance AgentThe core tasks of a financial analyst, done as an agent with research tools | 58.83%#23 of 31 | — |
| Finance IndexVals AI’s composite of finance tasks | 61.66%#5 of 31 | — |
| Tax Agent BenchAgentic research into US corporate tax questions | 32.09%#22 of 76 | — |
| Vals AI, law | ||
| Legal IndexVals AI’s composite of legal tasks | 73.90%#5 of 28 | — |
| Legal Research BenchAgentic US legal research | 46.15%#17 of 85 | — |
| Vals AI, medicine | ||
| MedCodeAssigning the right medical billing codes from clinical notes | 40.67%#62 of 107 | 52.20%#14 of 107 |
| MedQAMedical licensing exam questions, measured on accuracy and on robustness to bias | — | 96.03%#8 of 92 |
| Vals AI, reasoning | ||
| GPQA DiamondGraduate-level questions in biology, physics and chemistry that experts answer well and search does not | 93.69%#6 of 138 | 91.67%#19 of 138 |
| MMLU-ProHarder, reasoning-focused multiple choice across 14 subjects, from law to engineering | 88.60%#18 of 138 | 90.10%#7 of 138 |
| AIMEProblems from the American Invitational Mathematics Examination, a qualifier for the US Math Olympiad | — | 96.68%#4 of 96 |
| MMMUCollege-level questions that need both an image and text | 88.03%#12 of 93 | 87.51%#14 of 93 |
| Terminal-Bench ScienceExpert-written scientific research workflows, run by an agent in a terminal | 12.86%#13 of 42 | — |
Add models in the compare tool.
Questions
Which is better, Qwen3.8-Max or Gemini 3 Pro?
Qwen3.8-Max and Gemini 3 Pro are level on LMArena’s text leaderboard (1484 and 1480). On the 7 Vals AI benchmarks both have taken, Qwen3.8-Max wins 5 and Gemini 3 Pro wins 2 (Qwen3.8-Max: SWE-bench, Vibe Code Bench, LiveCodeBench).