AI BENCHY Compare
DeepSeek: DeepSeek V3.2 vs OpenAI: gpt-oss-120b
Last updated at: 2026-03-03
| Metric | DeepSeek: DeepSeek V3.2 none Release: 2025-12-01 | OpenAI: gpt-oss-120b medium Release: 2025-08-05 Free Available |
|---|---|---|
| Rank | #30 | #26 |
| Avg Score | 4.70 | 5.64 |
| Consistency | 8.19 | 7.55 |
| Cost per result | 0.132 | 0.101 |
| Total Cost | $0.007 | $0.008 |
| Tests Correct | 5/14 | 7/14 |
| Attempt pass rate | 47.6% | 59.5% |
| Flaky tests | 3 | 4 |
| Output Tokens | 4,869 | 11,407 |
| Reasoning Tokens | 0 | 26,106 |
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 | |
| OpenAI: gpt-oss-120b | 7.00 | 9.81 | 66.7% | 0 | 3,463 | 2,077 |
| 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 | |
| OpenAI: gpt-oss-120b | 5.50 | 5.87 | 66.7% | 1 | 241 | 1,114 |
| 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 | |
| OpenAI: gpt-oss-120b | 1.00 | 4.41 | 22.2% | 2 | 6,018 | 18,520 |
| 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 | |
| OpenAI: gpt-oss-120b | 10.00 | 10.00 | 100.0% | 0 | 120 | 1,770 |
| 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 | |
| OpenAI: gpt-oss-120b | 5.00 | 7.13 | 44.4% | 1 | 1,278 | 1,542 |
| 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 | |
| OpenAI: gpt-oss-120b | 9.00 | 9.97 | 100.0% | 0 | 287 | 1,083 |
Quick Compare
Switch Comparison Pair
gpt-oss-120bmediumFree AvailablevsGLM 5nonegpt-oss-120bmediumFree AvailablevsQwen3.5-122B-A10BnoneDeepSeek V3.2nonevsGLM 4.7 Flashmediumgpt-oss-120bmediumFree AvailablevsQwen3.5 Plus 2026-02-15noneClaude Sonnet 4.6nonevsgpt-oss-120bmediumFree AvailableDeepSeek V3.2nonevsMiniMax M2.5mediumgpt-oss-120bmediumFree AvailablevsQwen3.5-27Bnonegpt-oss-120bmediumFree AvailablevsQwen3.5-35B-A3BnoneDeepSeek V3.2nonevsQwen3.5-FlashmediumDeepSeek V3.2nonevsGPT-5 NanomediumDeepSeek V3.2nonevsQwen3 Coder NextmediumDeepSeek V3.2nonevsQwen3.5-35B-A3Bmedium