AI BENCHY Compare
Google: Gemini 2.5 Flash vs Google: Gemini 3 Flash Preview
Compare:
Last updated at: 2026-03-03
| Metric | Google: Gemini 2.5 Flash medium Release: 2025-06-17 | Google: Gemini 3 Flash Preview medium Release: 2025-12-17 |
|---|---|---|
| Rank | #16 | #1 |
| Avg Score | 7.05 | 9.93 |
| Consistency | 9.39 | 10.00 |
| Cost per result | 2.762 | 0.815 |
| Total Cost | $0.249 | $0.114 |
| Tests Correct | ||
| Attempt pass rate | 69.1% | 100.0% |
| Flaky tests | 1 | 0 |
| Output Tokens | 975 | 1,111 |
| Reasoning Tokens | 96,701 | 34,409 |
Score vs Total Cost
Category Breakdown
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 7.33 | 10.00 | 66.7% | 0 | 249 | 8,832 | |
| Google: Gemini 3 Flash Preview | 10.00 | 10.00 | 100.0% | 0 | 299 | 3,127 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 9.88 | 10.00 | 100.0% | 0 | 279 | 2,325 | |
| Google: Gemini 3 Flash Preview | 10.00 | 10.00 | 100.0% | 0 | 292 | 5,467 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 4.00 | 7.21 | 55.6% | 1 | 18 | 80,702 | |
| Google: Gemini 3 Flash Preview | 10.00 | 10.00 | 100.0% | 0 | 12 | 15,295 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 7.00 | 9.91 | 50.0% | 0 | 69 | 1,203 | |
| Google: Gemini 3 Flash Preview | 10.00 | 10.00 | 100.0% | 0 | 72 | 4,092 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 7.00 | 10.00 | 66.7% | 0 | 126 | 2,499 | |
| Google: Gemini 3 Flash Preview | 9.67 | 10.00 | 100.0% | 0 | 202 | 5,298 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 10.00 | 10.00 | 100.0% | 0 | 234 | 1,140 | |
| Google: Gemini 3 Flash Preview | 10.00 | 10.00 | 100.0% | 0 | 234 | 1,130 |
Quick Compare
Switch Comparison Pair
Gemini 2.5 FlashmediumvsGPT-5.3 ChatnoneGemini 2.5 FlashmediumvsGPT-5.2 ChatnoneClaude Sonnet 4.6nonevsGemini 2.5 FlashmediumGemini 2.5 FlashmediumvsQwen3.5 Plus 2026-02-15noneGemini 2.5 FlashmediumvsGLM 5noneGemini 2.5 FlashmediumvsQwen3.5-122B-A10BnoneGemini 2.5 FlashmediumvsGPT-4o-mininoneDeepSeek V3.2nonevsGemini 2.5 FlashmediumGemini 2.5 FlashmediumvsQwen3.5-27BnoneGemini 2.5 FlashmediumvsQwen3.5-35B-A3BnoneGemini 3 Flash PreviewmediumvsGPT-5.2 ChatnoneGemini 3 Flash PreviewmediumvsGPT-5.3 Chatnone