#114 DeepSeek V4 Pro
none
Invalid SVG
- Cost
- $0.000
- Time
- 300.0s
- Tokens
- 0 tok
AI BENCHY Compare
DeepSeek: DeepSeek V4 Pro vs NVIDIA: Nemotron 3 Super
Summary
DeepSeek V4 Pro vs Nemotron 3 Super benchmark comparison: DeepSeek V4 Pro leads on average score with 5.7 vs 4.9. Nemotron 3 Super has the lower benchmark cost at $0.007 vs $0.025. Nemotron 3 Super is faster at 5.30s vs 12.38s, with pass rates of 42.9% vs 31.8%.
Recommended model: Nemotron 3 Super - Its score stays close to the best score here (4.9 vs 5.7), while costing about 4.0x less than DeepSeek V4 Pro.
Last updated at: 2026-06-10
| Metric | DeepSeek V4 Pro DeepSeek V4 Pro none | Nemotron 3 Super Nemotron 3 Super none Free Available |
|---|---|---|
| Score | 5.7 | 4.9 |
| Rank | #114 | #142 |
| Reliability | 8.5 | 10.0 |
| Consistency | 8.5 | 8.8 |
| Tests Correct | ||
| Attempt pass rate | 42.9% | 31.8% |
| Flaky tests | 4 | 3 |
| Total Runs | 63 | 63 |
| Cost per result | 0.660 | 0.034 |
| Total Cost | $0.025 | $0.007 |
| Input Price | $0.435 / 1M | $0.090 / 1M |
| Output Price | $0.870 / 1M | $0.450 / 1M |
| Total Input Tokens | 44,845 | 36,456 |
| Output Tokens | 5,349 | 6,195 |
| Reasoning Tokens | 0 | 0 |
| Response Time (avg) | 12.38s | 5.30s |
| Response Time (max) | 58.65s | 16.45s |
| Response Time (total) | 260.06s | 111.31s |
Generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#142 Nemotron 3 Super
none
No showcase result has been generated for this model yet.
- Cost
- $0.000
- 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
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 3.5 | 8.0 | 16.7% | 1 | 14.02s | 540 | 704 | 0 | |
| Nemotron 3 Super | 4.8 | 10.0 | 25.0% | 0 | 4.46s | 671 | 2,322 | 0 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 4.6 | 7.9 | 22.2% | 1 | 6.11s | 7,279 | 531 | 0 | |
| Nemotron 3 Super | 3.3 | 7.2 | 11.1% | 1 | 2.64s | 7,627 | 571 | 0 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 9.5 | 10.0 | 100.0% | 0 | 25.49s | 20,773 | 1,911 | 0 | |
| Nemotron 3 Super | 3.0 | 10.0 | 0.0% | 0 | 16.45s | 8,740 | 617 | 0 |
| 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 | 6.9 | 5.8 | 66.7% | 1 | 30.54s | 5,633 | 170 | 0 | |
| Nemotron 3 Super | 10.0 | 10.0 | 100.0% | 0 | 7.92s | 7,944 | 249 | 0 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 5.3 | 10.0 | 33.3% | 0 | 3.17s | 666 | 18 | 0 | |
| Nemotron 3 Super | 3.6 | 7.2 | 22.2% | 1 | 6.23s | 789 | 26 | 0 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 4.3 | 9.9 | 0.0% | 0 | 3.75s | 471 | 132 | 0 | |
| Nemotron 3 Super | 4.6 | 10.0 | 0.0% | 0 | 950ms | 500 | 134 | 0 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 6.3 | 10.0 | 50.0% | 0 | 8.23s | 627 | 64 | 0 | |
| Nemotron 3 Super | 6.3 | 10.0 | 50.0% | 0 | 804ms | 723 | 66 | 0 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 7.6 | 7.2 | 77.8% | 1 | 15.95s | 594 | 173 | 0 | |
| Nemotron 3 Super | 5.5 | 10.0 | 33.3% | 0 | 2.36s | 714 | 1,125 | 0 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 10.0 | 10.0 | 100.0% | 0 | 5.92s | 8,079 | 219 | 0 | |
| Nemotron 3 Super | 4.7 | 1.6 | 66.7% | 1 | 16.00s | 8,541 | 281 | 0 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 3.0 | 10.0 | 0.0% | 0 | 15.59s | 183 | 1,427 | 0 | |
| Nemotron 3 Super | 3.0 | 10.0 | 0.0% | 0 | 8.94s | 207 | 804 | 0 |
Quick Compare
Switch Comparison Pair
CobuddymediumvsDeepSeek V4 PrononeDeepSeek V4 PrononevsNemotron 3 SupermediumFree AvailableNemotron 3 SupernoneFree AvailablevsQwen3 Coder NextmediumMistral Small 4mediumvsNemotron 3 SupernoneFree AvailableMiniMax M2.7mediumvsNemotron 3 SupernoneFree AvailableDeepSeek V4 PrononevsMiniMax M2.5mediumMiniMax M2.5mediumvsNemotron 3 SupernoneFree AvailableDeepSeek V4 PrononevsMiniMax M2.7mediumDeepSeek V4 PrononevsMistral Small 4mediumDeepSeek V4 Prononevsgpt-oss-120bmediumFree AvailableNemotron 3 SupernoneFree AvailablevsGLM 4.7 FlashmediumDeepSeek V4 PrononevsGPT-5 Nanomedium