- Rank
- #90
- Total Output Tokens
- 371,547
- Response Time (avg)
- 28.04s
- Total Cost
- $0.153
DeepSeek V4.1 Flash (low) vs Nemotron 3 Ultra (medium)
The average score is effectively tied at 8.0 vs 8.0. DeepSeek V4.1 Flash (low) has the lower benchmark cost at $0.153 vs $0.762. DeepSeek V4.1 Flash (low) is faster at 28.04s vs 40.33s, with pass rates of 73.9% vs 68.1%.
Compared models
- Rank
- #92
- Total Output Tokens
- 203,522
- Response Time (avg)
- 40.33s
- Total Cost
- $0.762
Recommended model
DeepSeek V4.1 Flash (low)
It has the best score here (8.0), while costing about 5.0x less than Nemotron 3 Ultra (medium).
Detailed comparison
| Metric | DeepSeek V4.1 Flash DeepSeek V4.1 Flash low | Nemotron 3 Ultra Nemotron 3 Ultra medium Free Available |
|---|---|---|
| Score | 8.0 | 8.0 |
| Rank | #90 | #92 |
| Reliability | 9.6 | 9.8 |
| Consistency | 8.7 | 8.9 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 73.9% | 68.1% |
| Flaky tests | 4 | 3 |
| Total Runs | 69 | 69 |
| Cost per result | 1.576 | 0.000 |
| Total Cost | $0.153 | $0.762 |
| Input Price | $0.020 / 1M | $0.600 / 1M |
| Output Price | $0.396 / 1M | $2.400 / 1M |
| Total Input Tokens | 266,849 | 482,754 |
| Output Tokens | 8,284 | 62,455 |
| Reasoning Tokens | 363,263 | 141,067 |
| Response Time (avg) | 28.04s | 40.33s |
| Response Time (max) | 149.84s | 392.56s |
| Response Time (total) | 645.03s | 927.65s |
| Parameters | 748B total (16B active) | 550B total (55B active) |
| Availability | Open source | Weights available |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#90 DeepSeek V4.1 Flash
low- Cost
- $0.017
- Time
- 43.6s
- Tokens
- 14,069 tok
#92 Nemotron 3 Ultra
medium
Reached the allocated time limit (300 seconds) without receiving showcase output.
- Cost
- $0.000
- Time
- 300.0s
- 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 V4.1 Flash | 6.1 | 3.1 | 66.7% | 1 | 56.02s | 167,134 | 1,903 | 21,681 | |
| Nemotron 3 Ultra | 10.0 | 10.0 | 100.0% | 0 | 188.06s | 249,339 | 8,071 | 11,046 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 8.3 | 10.0 | 75.0% | 0 | 3.32s | 852 | 171 | 4,328 | |
| Nemotron 3 Ultra | 10.0 | 10.0 | 100.0% | 0 | 8.62s | 780 | 835 | 1,485 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 40.66s | 7,509 | 378 | 81,978 | |
| Nemotron 3 Ultra | 8.4 | 7.4 | 88.9% | 1 | 26.53s | 7,686 | 2,854 | 17,725 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 24.73s | 77,368 | 4,906 | 24,016 | |
| Nemotron 3 Ultra | 6.3 | 5.8 | 66.7% | 1 | 218.25s | 204,249 | 40,954 | 78,561 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 6.5 | 10.0 | 50.0% | 0 | 3.80s | 2,397 | 120 | 1,149 | |
| Nemotron 3 Ultra | 10.0 | 10.0 | 100.0% | 0 | 5.68s | 7,989 | 473 | 1,285 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 3.5 | 4.4 | 33.3% | 2 | 95.58s | 909 | 27 | 184,701 | |
| Nemotron 3 Ultra | 3.6 | 7.2 | 22.2% | 1 | 35.22s | 785 | 7,637 | 18,208 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 4.34s | 549 | 117 | 1,319 | |
| Nemotron 3 Ultra | 3.7 | 9.5 | 0.0% | 0 | 2.52s | 360 | 70 | 235 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 8.38s | 783 | 63 | 1,546 | |
| Nemotron 3 Ultra | 9.8 | 10.0 | 100.0% | 0 | 6.35s | 765 | 182 | 1,243 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 8.2 | 7.7 | 77.8% | 1 | 9.39s | 828 | 273 | 14,502 | |
| Nemotron 3 Ultra | 5.5 | 9.9 | 33.3% | 0 | 3.54s | 792 | 771 | 2,055 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 13.83s | 8,259 | 313 | 284 | |
| Nemotron 3 Ultra | 10.0 | 10.0 | 100.0% | 0 | 7.72s | 9,781 | 304 | 984 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 3.0 | 10.0 | 0.0% | 0 | 46.86s | 261 | 13 | 27,759 | |
| Nemotron 3 Ultra | 3.0 | 10.0 | 0.0% | 0 | 38.47s | 228 | 304 | 8,240 |
Quick Compare
Switch Comparison Pair
Nemotron 3 UltramediumFree AvailablevsGPT-5.6 LunahighClaude Opus 4.7mediumvsDeepSeek V4.1 FlashlowDeepSeek V4.1 FlashlowvsGPT-5.6 LunahighNemotron 3 UltramediumFree AvailablevsGPT-5.6 TerralowDeepSeek V4.1 FlashlowvsGPT-5.4 NanomediumDeepSeek V4.1 FlashlowvsGemini 3.8 FlashmediumNemotron 3 UltramediumFree AvailablevsGLM 5.3 FlashXmaxDeepSeek V4 Flash 0423highvsNemotron 3 UltramediumFree AvailableClaude Fable 5.1highvsNemotron 3 UltramediumFree AvailableDeepSeek V4 Pro 0423highvsNemotron 3 UltramediumFree AvailableNemotron 3 UltramediumFree AvailablevsQwen3.7 MaxnoneDeepSeek V4.1 FlashlowvsQwen3.5-27Bmedium