AI BENCHY Compare
DeepSeek: DeepSeek V3.2 vs OpenAI: GPT-5.2
Last updated at: 2026-03-03
| Metric | DeepSeek: DeepSeek V3.2 medium Release: 2025-12-01 | OpenAI: GPT-5.2 medium Release: 2025-12-11 |
|---|---|---|
| Rank | #12 | #13 |
| Avg Score | 6.98 | 6.93 |
| Consistency | 8.75 | 8.22 |
| Cost per result | 0.193 | 2.780 |
| Total Cost | $0.018 | $0.251 |
| Tests Correct | 9/14 | 9/14 |
| Attempt pass rate | 71.4% | 76.2% |
| Flaky tests | 2 | 3 |
| Output Tokens | 6,753 | 1,869 |
| Reasoning Tokens | 30,427 | 14,190 |
Category Breakdown
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 7.00 | 9.86 | 66.7% | 0 | 1,171 | 4,893 | |
| OpenAI: GPT-5.2 | 7.00 | 7.28 | 77.8% | 1 | 549 | 2,002 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 9.88 | 10.00 | 100.0% | 0 | 207 | 7,693 | |
| OpenAI: GPT-5.2 | 10.00 | 10.00 | 100.0% | 0 | 234 | 499 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 4.00 | 7.21 | 44.4% | 1 | 3,081 | 7,856 | |
| OpenAI: GPT-5.2 | 4.00 | 7.21 | 55.6% | 1 | 42 | 9,690 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 7.00 | 9.84 | 50.0% | 0 | 1,397 | 2,845 | |
| OpenAI: GPT-5.2 | 9.50 | 10.00 | 100.0% | 0 | 95 | 587 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 7.00 | 7.21 | 88.9% | 1 | 390 | 6,281 | |
| OpenAI: GPT-5.2 | 8.00 | 10.00 | 66.7% | 0 | 710 | 943 |
| 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 | 507 | 859 | |
| OpenAI: GPT-5.2 | 1.00 | 1.62 | 66.7% | 1 | 239 | 469 |
Quick Compare
Switch Comparison Pair
DeepSeek V3.2mediumvsGemini 3 Flash PreviewnoneGemini 3 Flash PreviewnonevsGPT-5.2mediumClaude Sonnet 4.6nonevsGPT-5.2mediumClaude Sonnet 4.6nonevsDeepSeek V3.2mediumGPT-5.2mediumvsQwen3.5 Plus 2026-02-15noneDeepSeek V3.2mediumvsQwen3.5 Plus 2026-02-15noneGPT-5.2mediumvsGLM 5noneDeepSeek V3.2mediumvsGLM 5noneDeepSeek V3.2mediumvsGemini 3 Flash PreviewlowGemini 3 Flash PreviewlowvsGPT-5.2mediumGPT-5.2mediumvsQwen3.5-122B-A10BnoneDeepSeek V3.2mediumvsQwen3.5-122B-A10Bnone