- Rank
- #88
- Total Output Tokens
- 57,978
- Response Time (avg)
- 14.12s
- Total Cost
- $3.636
Claude Opus 4.7 (medium) vs DeepSeek V4 Pro 0423 (high)
The average score is effectively tied at 8.1 vs 8.1. DeepSeek V4 Pro 0423 (high) has the lower benchmark cost at $0.556 vs $3.636. Claude Opus 4.7 (medium) is faster at 14.12s vs 91.29s, with pass rates of 81.2% vs 65.2%.
Compared models
- Rank
- #87
- Total Output Tokens
- 228,663
- Response Time (avg)
- 91.29s
- Total Cost
- $0.556
Recommended model
Claude Opus 4.7 (medium)
It has the best score here (8.1), while responding about 6.5x faster than DeepSeek V4 Pro 0423 (high).
Detailed comparison
| Metric | Claude Opus 4.7 Claude Opus 4.7 medium | DeepSeek V4 Pro 0423 DeepSeek V4 Pro 0423 high |
|---|---|---|
| Score | 8.1 | 8.1 |
| Rank | #88 | #87 |
| Reliability | 10.0 | 10.0 |
| Consistency | 9.3 | 7.8 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 81.2% | 65.2% |
| Flaky tests | 2 | 6 |
| Total Runs | 69 | 69 |
| Cost per result | 20.200 | 3.717 |
| Total Cost | $3.636 | $0.556 |
| Input Price | $5.000 / 1M | $0.783 / 1M |
| Output Price | $25.000 / 1M | $1.566 / 1M |
| Total Input Tokens | 437,293 | 287,061 |
| Output Tokens | 29,102 | 32,056 |
| Reasoning Tokens | 28,876 | 196,607 |
| Response Time (avg) | 14.12s | 91.29s |
| Response Time (max) | 150.60s | 416.76s |
| Response Time (total) | 310.55s | 2099.56s |
| Parameters | ~5T total (~500B active) | 1.6T total (49B active) |
| Availability | Closed | Open source |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#88 Claude Opus 4.7
medium- Cost
- $0.059
- Time
- 26.8s
- Tokens
- 2,475 tok
#87 DeepSeek V4 Pro 0423
high- Cost
- $0.023
- Time
- 257.6s
- Tokens
- 14,870 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 |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.7 | 5.2 | 3.2 | 33.3% | 1 | 150.60s | 292,044 | 4,154 | 23,834 | |
| DeepSeek V4 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 64.54s | 196,304 | 9,128 | 10,091 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.7 | 8.3 | 10.0 | 75.0% | 0 | 1.85s | 894 | 348 | 0 | |
| DeepSeek V4 Pro 0423 | 5.7 | 5.9 | 58.3% | 2 | 25.70s | 536 | 149 | 3,214 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.7 | 7.6 | 7.2 | 77.8% | 1 | 12.96s | 10,635 | 7,629 | 1,114 | |
| DeepSeek V4 Pro 0423 | 6.3 | 8.7 | 33.3% | 0 | 243.00s | 5,090 | 383 | 84,580 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.7 | 10.0 | 10.0 | 100.0% | 0 | 43.42s | 104,347 | 15,459 | 3,928 | |
| DeepSeek V4 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 78.99s | 66,082 | 4,582 | 25,404 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.7 | 10.0 | 10.0 | 100.0% | 0 | 2.37s | 10,533 | 324 | 0 | |
| DeepSeek V4 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 25.03s | 7,690 | 274 | 2,166 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.7 | 7.7 | 10.0 | 66.7% | 0 | 1.19s | 627 | 51 | 0 | |
| DeepSeek V4 Pro 0423 | 3.6 | 7.2 | 22.2% | 1 | 249.47s | 578 | 16,870 | 58,188 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.7 | 10.0 | 10.0 | 100.0% | 0 | 2.87s | 723 | 256 | 0 | |
| DeepSeek V4 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 8.83s | 471 | 115 | 1,013 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.7 | 10.0 | 10.0 | 100.0% | 0 | 1.57s | 939 | 114 | 0 | |
| DeepSeek V4 Pro 0423 | 7.8 | 6.6 | 83.3% | 1 | 8.73s | 627 | 66 | 2,726 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.7 | 10.0 | 10.0 | 100.0% | 0 | 2.43s | 939 | 370 | 0 | |
| DeepSeek V4 Pro 0423 | 6.9 | 4.9 | 77.8% | 2 | 56.85s | 591 | 178 | 2,563 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.7 | 10.0 | 10.0 | 100.0% | 0 | 4.17s | 15,339 | 373 | 0 | |
| DeepSeek V4 Pro 0423 | 9.8 | 10.0 | 100.0% | 0 | 15.92s | 8,909 | 295 | 701 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.7 | 3.0 | 10.0 | 0.0% | 0 | 2.25s | 273 | 24 | 0 | |
| DeepSeek V4 Pro 0423 | 3.0 | 10.0 | 0.0% | 0 | 34.01s | 183 | 16 | 5,961 |
Quick Compare
Switch Comparison Pair
Claude Opus 4.7mediumvsDeepSeek V4 Flash 0423highClaude Opus 4.7mediumvsDeepSeek V4.1 FlashlowSeed-2.0-CodelowvsDeepSeek V4 Pro 0423highClaude Opus 4.7mediumvsGPT-5.6 LunahighClaude Opus 4.7mediumvsSeed-2.0-CodelowSeed-2.0-LitemediumvsDeepSeek V4 Pro 0423highDeepSeek V4 Pro 0423highvsNemotron 3 UltramediumFree AvailableDeepSeek V4 Pro 0423highvsGPT-5.4 NanomediumDeepSeek V4 Pro 0423highvsGemini 3.8 FlashmediumClaude Opus 4.7mediumvsGPT-5.6 TerralowClaude Opus 4.7mediumvsGLM 5.3 FlashXmaxDeepSeek V4 Pro 0423highvsGPT-5.6 Terralow