Gemini 2.5 Flash (Jun 2025) benchmark results
9 results on 5 benchmarks from 4 sources.
Also listed as: gemini-2.5-flash · Gemini 2.5 Flash · Gemini 2.5 Flash (2025-04-17) · Gemini-2.5-Flash (FC) · Gemini-2.5-Flash (Prompt)
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1409 | 149 | Overall, style control on; 125562 votes; 95% CI 1407–1412“gemini-2.5-flash” | Official leaderboard | Oct 8, 2026 |
| LMArena Vision | 1215 | 76 | Overall, style control on; 60113 votes; 95% CI 1210–1220“gemini-2.5-flash” | Official leaderboard | Oct 2, 2026 |
| SWE-bench Verified | 28.7% | 92 | agent: mini-SWE-agent“gemini-2.5-flash” | Official leaderboard | Jul 26, 2025 |
| Terminal-Bench 2.0 | 17.1% | 170 | Terminal-Bench 2.0; agent: Mini-SWE-Agent | Official leaderboard via Epoch AI | Jun 17, 2025 |
| Terminal-Bench 2.0 | 16.9% | 172 | Terminal-Bench 2.0; agent: Terminus 2 | Official leaderboard via Epoch AI | Jun 17, 2025 |
| Terminal-Bench 2.0 | 16.4% | 173 | Terminal-Bench 2.0; agent: OpenHands | Official leaderboard via Epoch AI | Jun 17, 2025 |
| Terminal-Bench 2.0 | 15.4% | 177 | Terminal-Bench 2.0; agent: Gemini CLI | Official leaderboard via Epoch AI | Jun 17, 2025 |
| BFCL v4 (function calling) | 56.2% | 15 | Overall accuracy; native function calling (FC)“Gemini-2.5-Flash (FC)” | Official leaderboard | Oct 17, 2026 |
| BFCL v4 (function calling) | 50.9% | 26 | Overall accuracy; prompt-based“Gemini-2.5-Flash (Prompt)” | Official leaderboard | Oct 17, 2026 |
Related on this site
FAQ
Where do these Gemini 2.5 Flash (Jun 2025) scores come from?
From Berkeley Function Calling Leaderboard (BFCL), LMArena leaderboard dataset, SWE-bench leaderboards (swebench.com), and Epoch AI Benchmarking Hub. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.