- Rank
- #87
- Total Output Tokens
- 228,663
- Response Time (avg)
- 91.29s
- Total Cost
- $0.556
DeepSeek V4 Pro 0423 (high) vs GPT-5.6 Terra (medium)
GPT-5.6 Terra (medium) leads on average score with 8.2 vs 8.1. DeepSeek V4 Pro 0423 (high) has the lower benchmark cost at $0.556 vs $0.744. GPT-5.6 Terra (medium) is faster at 8.93s vs 91.29s, with pass rates of 65.2% vs 71.0%.
Compared models
- Rank
- #84
- Total Output Tokens
- 33,189
- Response Time (avg)
- 8.93s
- Total Cost
- $0.744
Recommended model
GPT-5.6 Terra (medium)
It has the best score here (8.2), while responding about 10.2x faster than DeepSeek V4 Pro 0423 (high).
Detailed comparison
| Metric | DeepSeek V4 Pro 0423 DeepSeek V4 Pro 0423 high | GPT-5.6 Terra GPT-5.6 Terra medium |
|---|---|---|
| Score | 8.1 | 8.2 |
| Rank | #87 | #84 |
| Reliability | 10.0 | 10.0 |
| Consistency | 7.8 | 9.3 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 65.2% | 71.0% |
| Flaky tests | 6 | 2 |
| Total Runs | 69 | 69 |
| Cost per result | 3.717 | 5.768 |
| Total Cost | $0.556 | $0.744 |
| Input Price | $0.783 / 1M | $2.000 / 1M |
| Output Price | $1.566 / 1M | $12.000 / 1M |
| Total Input Tokens | 287,061 | 172,507 |
| Output Tokens | 32,056 | 5,824 |
| Reasoning Tokens | 196,607 | 27,365 |
| Response Time (avg) | 91.29s | 8.93s |
| Response Time (max) | 416.76s | 54.74s |
| Response Time (total) | 2099.56s | 205.39s |
| Parameters | 1.6T total (49B active) | ~1T total (~60B active) |
| Availability | Open source | Closed |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#87 DeepSeek V4 Pro 0423
high- Cost
- $0.023
- Time
- 257.6s
- Tokens
- 14,870 tok
#84 GPT-5.6 Terra
medium- Cost
- $0.035
- Time
- 16.3s
- Tokens
- 2,418 tok
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Category Breakdown
| Agentic | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 64.54s | 196,304 | 9,128 | 10,091 | |
| GPT-5.6 Terra | 10.0 | 10.0 | 100.0% | 0 | 54.74s | 93,323 | 946 | 1,894 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | 5.7 | 5.9 | 58.3% | 2 | 25.70s | 536 | 149 | 3,214 | |
| GPT-5.6 Terra | 8.3 | 10.0 | 75.0% | 0 | 2.22s | 606 | 172 | 657 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | 6.3 | 8.7 | 33.3% | 0 | 243.00s | 5,090 | 383 | 84,580 | |
| GPT-5.6 Terra | 6.1 | 7.2 | 55.6% | 1 | 7.19s | 7,302 | 427 | 4,527 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 78.99s | 66,082 | 4,582 | 25,404 | |
| GPT-5.6 Terra | 10.0 | 10.0 | 100.0% | 0 | 11.10s | 55,976 | 3,212 | 2,122 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 25.03s | 7,690 | 274 | 2,166 | |
| GPT-5.6 Terra | 10.0 | 10.0 | 100.0% | 0 | 872ms | 7,140 | 222 | 0 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | 3.6 | 7.2 | 22.2% | 1 | 249.47s | 578 | 16,870 | 58,188 | |
| GPT-5.6 Terra | 5.3 | 10.0 | 33.3% | 0 | 21.52s | 732 | 70 | 13,846 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 8.83s | 471 | 115 | 1,013 | |
| GPT-5.6 Terra | 5.5 | 10.0 | 0.0% | 0 | 2.37s | 477 | 133 | 144 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | 7.8 | 6.6 | 83.3% | 1 | 8.73s | 627 | 66 | 2,726 | |
| GPT-5.6 Terra | 10.0 | 10.0 | 100.0% | 0 | 1.43s | 660 | 89 | 261 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | 6.9 | 4.9 | 77.8% | 2 | 56.85s | 591 | 178 | 2,563 | |
| GPT-5.6 Terra | 8.4 | 7.4 | 88.9% | 1 | 3.78s | 642 | 272 | 1,462 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | 9.8 | 10.0 | 100.0% | 0 | 15.92s | 8,909 | 295 | 701 | |
| GPT-5.6 Terra | 10.0 | 10.0 | 100.0% | 0 | 5.09s | 5,454 | 254 | 246 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | 3.0 | 10.0 | 0.0% | 0 | 34.01s | 183 | 16 | 5,961 | |
| GPT-5.6 Terra | 3.0 | 10.0 | 0.0% | 0 | 10.05s | 195 | 27 | 2,206 |
Quick Compare
Switch Comparison Pair
GPT-5.6 TerramediumvsGrok 4.5highClaude Opus 4.7mediumvsDeepSeek V4 Pro 0423highSeed-2.0-CodelowvsDeepSeek V4 Pro 0423highKimi K3maxvsGPT-5.6 TerramediumSeed-2.0-LitemediumvsDeepSeek V4 Pro 0423highGemini 3.5 FlashhighvsGPT-5.6 TerramediumDeepSeek V4 Pro 0423highvsNemotron 3 UltramediumFree AvailableSeed-2.0-CodelowvsGPT-5.6 TerramediumDeepSeek V4 Pro 0423highvsGPT-5.4 NanomediumDeepSeek V4 Pro 0423highvsGemini 3.8 FlashmediumGPT-5.6 TerramediumvsGLM 5.2highDeepSeek V4 Pro 0423highvsGPT-5.6 Terralow