- Rank
- #222
- Total Output Tokens
- 143,160
- Response Time (avg)
- 70.08s
- Total Cost
- $0.145
DeepSeek V3.2 (medium) vs Solar Pro 4 (high)
The average score is effectively tied at 6.3 vs 6.3. DeepSeek V3.2 (medium) has the lower benchmark cost at $0.145 vs $0.164. DeepSeek V3.2 (medium) is faster at 70.08s vs 128.91s, with pass rates of 62.3% vs 60.9%.
Compared models
- Rank
- #219
- Total Output Tokens
- 402,203
- Response Time (avg)
- 128.91s
- Total Cost
- $0.164
Recommended model
DeepSeek V3.2 (medium)
It has the best score here (6.3), while responding about 1.8x faster than Solar Pro 4 (high).
Detailed comparison
| Metric | DeepSeek V3.2 DeepSeek V3.2 medium | Solar Pro 4 Solar Pro 4 high |
|---|---|---|
| Score | 6.3 | 6.3 |
| Rank | #222 | #219 |
| Reliability | 10.0 | 10.0 |
| Consistency | 7.5 | 8.0 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 62.3% | 60.9% |
| Flaky tests | 7 | 6 |
| Total Runs | 69 | 69 |
| Cost per result | 1.250 | 0.652 |
| Total Cost | $0.145 | $0.164 |
| Input Price | $0.280 / 1M | $0.090 / 1M |
| Output Price | $0.420 / 1M | $0.360 / 1M |
| Total Input Tokens | 306,662 | 209,002 |
| Output Tokens | 17,819 | 24,675 |
| Reasoning Tokens | 125,341 | 377,528 |
| Response Time (avg) | 70.08s | 128.91s |
| Response Time (max) | 376.10s | 491.07s |
| Response Time (total) | 1611.86s | 2965.04s |
| Parameters | 671B total (37B active) | ~100B |
| Availability | Open source | Closed |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#222 DeepSeek V3.2
medium- Cost
- $0.001
- Time
- 53.6s
- Tokens
- 1,932 tok
#219 Solar Pro 4
high
No showcase result has been generated for this model yet.
- Cost
- N/A
- Time
- -
- Tokens
- 0 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 V3.2 | 3.0 | 10.0 | 0.0% | 0 | 106.33s | 205,606 | 5,987 | 8,386 | |
| Solar Pro 4 | 2.8 | 1.6 | 33.3% | 1 | 312.27s | 129,262 | 1,318 | 37,691 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V3.2 | 8.2 | 7.9 | 83.3% | 1 | 24.23s | 448 | 3,247 | 6,953 | |
| Solar Pro 4 | 8.7 | 7.9 | 91.7% | 1 | 58.83s | 1,104 | 313 | 40,629 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V3.2 | 6.0 | 7.2 | 55.6% | 1 | 248.68s | 5,717 | 649 | 52,014 | |
| Solar Pro 4 | 5.7 | 9.9 | 33.3% | 0 | 244.73s | 7,887 | 18,577 | 101,928 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V3.2 | 7.3 | 5.8 | 83.3% | 1 | 79.92s | 76,997 | 5,219 | 24,229 | |
| Solar Pro 4 | 7.3 | 5.8 | 83.3% | 1 | 167.40s | 51,594 | 3,394 | 37,597 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V3.2 | 10.0 | 10.0 | 100.0% | 0 | 36.09s | 7,388 | 207 | 7,693 | |
| Solar Pro 4 | 10.0 | 10.0 | 100.0% | 0 | 62.46s | 7,575 | 252 | 22,209 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V3.2 | 2.9 | 4.4 | 22.2% | 2 | 22.94s | 481 | 19 | 6,779 | |
| Solar Pro 4 | 3.6 | 7.2 | 22.2% | 1 | 280.84s | 1,098 | 37 | 79,201 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V3.2 | 3.4 | 2.5 | 33.3% | 1 | 58.29s | 314 | 49 | 2,189 | |
| Solar Pro 4 | 5.5 | 10.0 | 0.0% | 0 | 42.22s | 609 | 123 | 7,474 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V3.2 | 10.0 | 10.0 | 100.0% | 0 | 35.78s | 627 | 1,397 | 2,845 | |
| Solar Pro 4 | 7.9 | 6.9 | 66.7% | 1 | 41.51s | 909 | 75 | 13,182 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V3.2 | 7.0 | 7.2 | 55.6% | 1 | 37.69s | 594 | 518 | 6,375 | |
| Solar Pro 4 | 8.7 | 7.9 | 77.8% | 1 | 55.22s | 1,017 | 345 | 23,424 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V3.2 | 10.0 | 10.0 | 100.0% | 0 | 34.81s | 8,307 | 507 | 859 | |
| Solar Pro 4 | 10.0 | 10.0 | 100.0% | 0 | 8.96s | 7,620 | 225 | 770 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V3.2 | 3.0 | 10.0 | 0.0% | 0 | 83.99s | 183 | 20 | 7,019 | |
| Solar Pro 4 | 3.0 | 10.0 | 0.0% | 0 | 81.13s | 327 | 16 | 13,423 |
Quick Compare
Switch Comparison Pair
Gemini 3.1 Flash LitelowvsSolar Pro 4highQwen3.5 Plus 2026-04-20nonevsSolar Pro 4highGemini 3.1 Flash Lite PreviewlowvsSolar Pro 4highSpace Bunny AlphamediumvsSolar Pro 4highGemini 3.5 Flash LitelowvsSolar Pro 4highDeepSeek V3.2mediumvsGemini 3.1 Flash LitelowDeepSeek V3.2mediumvsQwen3.5 Plus 2026-04-20noneDeepSeek V3.2mediumvsGemini 3.5 FlashnoneQwen3.6 27BnonevsSolar Pro 4highQwen3.5-35B-A3BmediumvsSolar Pro 4highLongCat 2.0nonevsSolar Pro 4highDeepSeek V3.2mediumvsGemini 3.1 Flash Lite Previewlow