- Rank
- #108
- Total Output Tokens
- 203,134
- Response Time (avg)
- 55.99s
- Total Cost
- $0.261
DeepSeek V4 Flash 0423 (high) vs GPT-5.6 Luna (high)
DeepSeek V4 Flash 0423 (high) leads on average score with 8.1 vs 8.0. GPT-5.6 Luna (high) has the lower benchmark cost at $0.118 vs $0.261. GPT-5.6 Luna (high) is faster at 18.39s vs 55.99s, with pass rates of 71.0% vs 71.0%.
Compared models
- Rank
- #110
- Total Output Tokens
- 139,395
- Response Time (avg)
- 18.39s
- Total Cost
- $0.118
Recommended model
GPT-5.6 Luna (high)
Its score stays close to the best score here (8.0 vs 8.1), while costing about 2.2x less than DeepSeek V4 Flash 0423 (high).
Detailed comparison
| Metric | DeepSeek V4 Flash 0423 DeepSeek V4 Flash 0423 high | GPT-5.6 Luna GPT-5.6 Luna high |
|---|---|---|
| Score | 8.1 | 8.0 |
| Rank | #108 | #110 |
| Reliability | 10.0 | 10.0 |
| Consistency | 8.6 | 8.6 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 71.0% | 71.0% |
| Flaky tests | 4 | 4 |
| Total Runs | 69 | 69 |
| Cost per result | 0.547 | 5.882 |
| Total Cost | $0.261 | $0.118 |
| Input Price | $0.002 / 1M | $0.200 / 1M |
| Output Price | $1.280 / 1M | $1.200 / 1M |
| Cache Read Price | $0.002 / 1M | $0.020 / 1M |
| Cache Write Price | N/A | $0.250 / 1M |
| Total Input Tokens | 298,794 | 197,896 |
| Output Tokens | 45,873 | 6,211 |
| Reasoning Tokens | 188,721 | 133,184 |
| Response Time (avg) | 55.99s | 18.39s |
| Response Time (max) | 218.13s | 111.09s |
| Response Time (total) | 1287.87s | 422.93s |
| Parameters | 284B total (13B active) | ~400B total (~17B active) |
| Availability | Open source | Closed |
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#108 DeepSeek V4 Flash 0423
high- Cost
- $0.003
- Time
- 93.1s
- Tokens
- 7,926 tok
#110 GPT-5.6 Luna
high- Cost
- $0.033
- Time
- 34.2s
- Tokens
- 5,484 tok
Category Breakdown
| Agentic | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 10.0 | 10.0 | 100.0% | 0 | 148.13s | 190,314 | 8,644 | 14,640 | |
| GPT-5.6 Luna | 10.0 | 10.0 | 100.0% | 0 | 60.15s | 116,969 | 1,123 | 2,957 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 8.3 | 10.0 | 75.0% | 0 | 28.51s | 540 | 140 | 7,770 | |
| GPT-5.6 Luna | 8.3 | 10.0 | 75.0% | 0 | 2.99s | 606 | 162 | 1,265 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 7.8 | 10.0 | 66.7% | 0 | 50.60s | 7,279 | 395 | 34,862 | |
| GPT-5.6 Luna | 5.5 | 4.7 | 55.6% | 2 | 15.63s | 7,302 | 510 | 17,746 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 6.4 | 5.8 | 66.7% | 1 | 104.10s | 82,663 | 4,633 | 37,533 | |
| GPT-5.6 Luna | 10.0 | 10.0 | 100.0% | 0 | 19.05s | 57,719 | 3,366 | 8,005 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 10.0 | 10.0 | 100.0% | 0 | 28.03s | 7,290 | 201 | 1,179 | |
| GPT-5.6 Luna | 10.0 | 10.0 | 100.0% | 0 | 2.18s | 7,140 | 234 | 470 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 3.6 | 7.2 | 22.2% | 1 | 115.42s | 754 | 22,778 | 79,643 | |
| GPT-5.6 Luna | 5.3 | 7.2 | 44.4% | 1 | 62.87s | 732 | 69 | 75,712 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 6.1 | 3.1 | 66.7% | 1 | 25.15s | 471 | 79 | 632 | |
| GPT-5.6 Luna | 5.0 | 10.0 | 0.0% | 0 | 3.65s | 477 | 117 | 563 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 10.0 | 10.0 | 100.0% | 0 | 15.36s | 627 | 63 | 1,622 | |
| GPT-5.6 Luna | 9.9 | 10.0 | 100.0% | 0 | 1.79s | 660 | 97 | 481 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 8.2 | 7.2 | 88.9% | 1 | 26.11s | 594 | 196 | 1,767 | |
| GPT-5.6 Luna | 7.6 | 7.2 | 77.8% | 1 | 14.55s | 642 | 242 | 18,281 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 10.0 | 10.0 | 100.0% | 0 | 74.73s | 8,079 | 228 | 542 | |
| GPT-5.6 Luna | 10.0 | 10.0 | 100.0% | 0 | 4.98s | 5,454 | 260 | 324 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 3.0 | 10.0 | 0.0% | 0 | 54.46s | 183 | 8,516 | 8,531 | |
| GPT-5.6 Luna | 3.0 | 10.0 | 0.0% | 0 | 17.00s | 195 | 31 | 7,380 |
Quick Compare
Switch Comparison Pair
Claude Opus 4.7mediumvsDeepSeek V4 Flash 0423highNemotron 3 UltramediumFree AvailablevsGPT-5.6 LunahighDeepSeek V4.1 FlashlowvsGPT-5.6 LunahighGemini 3.8 FlashmediumvsGPT-5.6 LunahighGPT-5.6 LunahighvsQwen3.8 Flash NextlowClaude Opus 4.7mediumvsGPT-5.6 LunahighSeed-2.0-CodelowvsDeepSeek V4 Flash 0423highDeepSeek V4 Flash 0423highvsNemotron 3 UltramediumFree AvailableGPT-5.6 LunahighvsQwen3.5-27BmediumGPT-5.6 LunahighvsGLM 5.3 FlashXmaxDeepSeek V4 Flash 0423highvsGPT-5.4 NanomediumDeepSeek V4 Flash 0423highvsGemini 3.8 Flashmedium