AI BENCHY Compare
DeepSeek: DeepSeek V3.2 vs Google: Gemini 2.5 Flash
Compare:
Last updated at: 2026-03-03
| Metric | DeepSeek: DeepSeek V3.2 none Release: 2025-12-01 | Google: Gemini 2.5 Flash none Release: 2025-06-17 |
|---|---|---|
| Rank | #39 | #36 |
| Avg Score | 4.70 | 5.34 |
| Consistency | 8.19 | 9.40 |
| Cost per result | 0.132 | 0.107 |
| Total Cost | $0.007 | $0.007 |
| Tests Correct | ||
| Attempt pass rate | 47.6% | 47.6% |
| Flaky tests | 3 | 1 |
| Output Tokens | 4,869 | 826 |
| Reasoning Tokens | 0 | 0 |
Score vs Total Cost
Category Breakdown
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 1.00 | 9.68 | 0.0% | 0 | 1,411 | 0 | |
| Google: Gemini 2.5 Flash | 1.00 | 10.00 | 0.0% | 0 | 99 | 0 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 5.38 | 5.81 | 66.7% | 1 | 1,710 | 0 | |
| Google: Gemini 2.5 Flash | 9.88 | 10.00 | 100.0% | 0 | 279 | 0 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 1.00 | 7.21 | 22.2% | 1 | 24 | 0 | |
| Google: Gemini 2.5 Flash | 4.00 | 7.21 | 55.6% | 1 | 12 | 0 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 8.00 | 9.99 | 50.0% | 0 | 66 | 0 | |
| Google: Gemini 2.5 Flash | 8.00 | 9.99 | 50.0% | 0 | 70 | 0 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 7.67 | 7.49 | 88.9% | 1 | 1,136 | 0 | |
| Google: Gemini 2.5 Flash | 4.67 | 10.00 | 33.3% | 0 | 132 | 0 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 10.00 | 10.00 | 100.0% | 0 | 522 | 0 | |
| Google: Gemini 2.5 Flash | 10.00 | 10.00 | 100.0% | 0 | 234 | 0 |
Quick Compare
Switch Comparison Pair
Gemini 2.5 FlashnonevsMiniMax M2.5mediumGemini 2.5 Flashnonevsgpt-oss-120bmediumFree AvailableGemini 2.5 FlashnonevsGPT-5 MinimediumGemini 2.5 FlashnonevsQwen3.5-FlashmediumGemini 2.5 FlashnonevsGPT-5 NanomediumDeepSeek V3.2nonevsGLM 4.7 FlashmediumGemini 2.5 FlashnonevsQwen3.5-35B-A3BmediumGemini 2.5 FlashnonevsMiMo-V2-FlashmediumClaude Opus 4.6mediumvsGemini 2.5 FlashnoneSeed-2.0-MinimediumvsGemini 2.5 FlashnoneGemini 2.5 FlashnonevsKimi K2.5mediumGemini 2.5 FlashnonevsGrok 4.1 Fastmedium