Compare / Gemini 3.8 Flash vs GPT-5.2
Gemini 3.8 Flash vs GPT-5.2
17 results from 5 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Gemini 3.8 Flash | GPT-5.2 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,477 | 1,442 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,482 | 1,444 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,482 | 1,391 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,529 | 1,475 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,488 | 1,427 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,492 | 1,437 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,486 | 1,411 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 40.9 | 30.4 |
| Artificial Analysisreported | GPQA Diamond% of questions | 95.3% | 90.3% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 47.8% | 37.7% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 84.0% | 82.7% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 45.8% | 11.1% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 69.7% | 37.1% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 13.0% | 76.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.34 | 0.40 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 78.5 | 49.4 |
| Vending-Bench 2reported | Money after a yearUS dollars | $5,093.79 | $3,591.33 |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.