AI BENCHY Compare
DeepSeek: DeepSeek V3.2 vs Qwen: Qwen3 Coder Next
Last updated at: 2026-03-03
| Metric | DeepSeek: DeepSeek V3.2 medium Release: 2025-12-01 | Qwen: Qwen3 Coder Next none Release: 2026-02-03 |
|---|---|---|
| Rank | #12 | #36 |
| Avg Score | 6.98 | 3.71 |
| Consistency | 8.75 | 9.53 |
| Cost per result | 0.193 | 0.138 |
| Total Cost | $0.018 | $0.005 |
| Tests Correct | 9/14 | 3/14 |
| Attempt pass rate | 71.4% | 26.2% |
| Flaky tests | 2 | 1 |
| Output Tokens | 6,753 | 2,688 |
| Reasoning Tokens | 30,427 | 0 |
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 | |
| Qwen: Qwen3 Coder Next | 2.33 | 9.99 | 0.0% | 0 | 1,315 | 0 |
| 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 | |
| Qwen: Qwen3 Coder Next | 5.50 | 10.00 | 50.0% | 0 | 276 | 0 |
| 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 | |
| Qwen: Qwen3 Coder Next | 4.00 | 10.00 | 33.3% | 0 | 24 | 0 |
| 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 | |
| Qwen: Qwen3 Coder Next | 4.50 | 6.88 | 33.3% | 1 | 63 | 0 |
| 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 | |
| Qwen: Qwen3 Coder Next | 1.00 | 9.92 | 0.0% | 0 | 755 | 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 | 507 | 859 | |
| Qwen: Qwen3 Coder Next | 10.00 | 10.00 | 100.0% | 0 | 255 | 0 |
Quick Compare
Switch Comparison Pair
DeepSeek V3.2mediumvsGemini 3 Flash PreviewnoneQwen3 Coder NextnonevsGLM 4.7 FlashmediumClaude Sonnet 4.6nonevsDeepSeek V3.2mediumDeepSeek V3.2mediumvsQwen3.5 Plus 2026-02-15noneDeepSeek V3.2mediumvsGLM 5noneDeepSeek V3.2mediumvsGemini 3 Flash PreviewlowDeepSeek V3.2mediumvsQwen3.5-122B-A10BnoneMiniMax M2.5mediumvsQwen3 Coder Nextnonegpt-oss-120bmediumFree AvailablevsQwen3 Coder NextnoneDeepSeek V3.2mediumvsGPT-4o-mininoneGPT-5 NanomediumvsQwen3 Coder NextnoneQwen3 Coder NextnonevsMiMo-V2-Flashmedium