AI BENCHY Compare
DeepSeek: DeepSeek V3.2 vs Inception: Mercury 2
Compare:
Last updated at: 2026-03-05
| Metric | DeepSeek: DeepSeek V3.2 none Release: 2025-12-01 | Inception: Mercury 2 medium Release: 2026-02-24 |
|---|---|---|
| Rank | #38 | #40 |
| Avg Score | 49 | 48 |
| Consistency | 83 | 83 |
| Cost per result | 0.304 | 0.726 |
| Total Cost | $0.016 | $0.044 |
| Tests Correct | ||
| Attempt pass rate | 44.4% | 51.1% |
| Flaky tests | 3 | 3 |
| Output Tokens | 7,756 | 3,571 |
| Reasoning Tokens | 0 | 45,379 |
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 | 100 | 97 | 0.0% | 0 | 1,411 | 0 | |
| Inception: Mercury 2 | 73 | 98 | 66.7% | 0 | 2,531 | 2,410 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 80 | 100 | 0.0% | 0 | 2,887 | 0 | |
| Inception: Mercury 2 | 100 | 100 | 100.0% | 0 | 268 | 4,887 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 54 | 58 | 66.7% | 1 | 1,710 | 0 | |
| Inception: Mercury 2 | 55 | 59 | 83.3% | 1 | 183 | 1,656 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 100 | 72 | 22.2% | 1 | 24 | 0 | |
| Inception: Mercury 2 | 100 | 72 | 11.1% | 1 | 41 | 30,754 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 80 | 100 | 50.0% | 0 | 66 | 0 | |
| Inception: Mercury 2 | 55 | 100 | 50.0% | 0 | 14 | 958 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 77 | 75 | 88.9% | 1 | 1,136 | 0 | |
| Inception: Mercury 2 | 17 | 75 | 22.2% | 1 | 354 | 2,758 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 100 | 100 | 100.0% | 0 | 522 | 0 | |
| Inception: Mercury 2 | 100 | 100 | 100.0% | 0 | 180 | 1,956 |
Quick Compare
Switch Comparison Pair
Mercury 2mediumvsQwen3.5-122B-A10BnoneMercury 2mediumvsQwen3.5-FlashnoneMercury 2mediumvsQwen3.5-27BnoneDeepSeek V3.2nonevsgpt-oss-120bmediumFree AvailableMercury 2mediumvsQwen3.5-35B-A3BnoneGemini 2.5 FlashnonevsMercury 2mediumDeepSeek V3.2nonevsMiniMax M2.5mediumMercury 2mediumvsGPT-5.4noneDeepSeek V3.2nonevsGPT-5 NanomediumDeepSeek V3.2nonevsQwen3.5-35B-A3BmediumTrinity Large Preview (free)noneFree AvailablevsMercury 2mediumMercury 2mediumvsGPT-4o-mininone