- Rank
- #296
- Total Output Tokens
- 16,806
- Response Time (avg)
- 3.46s
- Total Cost
- $0.055
DeepSeek V4.1 Flash 1017 vs Nemotron 3 Ultra
The average score is effectively tied at 5.8 vs 5.9. DeepSeek V4.1 Flash 1017 has the lower benchmark cost at $0.055 vs $0.164. DeepSeek V4.1 Flash 1017 is faster at 3.46s vs 6.76s, with pass rates of 36.2% vs 40.6%.
Compared models
- Rank
- #293
- Total Output Tokens
- 11,544
- Response Time (avg)
- 6.76s
- Total Cost
- $0.164
Recommended model
DeepSeek V4.1 Flash 1017
It has the best score here (5.8), while costing about 3.0x less than Nemotron 3 Ultra.
Detailed comparison
| Metric | DeepSeek V4.1 Flash 1017 DeepSeek V4.1 Flash 1017 none | Nemotron 3 Ultra Nemotron 3 Ultra none Free Available |
|---|---|---|
| Score | 5.8 | 5.9 |
| Rank | #296 | #293 |
| Reliability | 10.0 | 10.0 |
| Consistency | 9.7 | 9.3 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 36.2% | 40.6% |
| Flaky tests | 1 | 2 |
| Total Runs | 69 | 69 |
| Cost per result | 0.678 | 0.000 |
| Total Cost | $0.055 | $0.164 |
| Input Price | $0.150 / 1M | $0.500 / 1M |
| Output Price | $0.600 / 1M | $2.200 / 1M |
| Cache Read Price | $0.003 / 1M | $0.100 / 1M |
| Cache Write Price | N/A | N/A |
| Total Input Tokens | 293,927 | 275,381 |
| Output Tokens | 16,806 | 11,544 |
| Reasoning Tokens | 0 | 0 |
| Response Time (avg) | 3.46s | 6.76s |
| Response Time (max) | 43.95s | 70.17s |
| Response Time (total) | 79.48s | 155.50s |
| Parameters | ~748B total (~16B active) | 550B total (55B active) |
| Availability | Open source | Weights available |
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#296 DeepSeek V4.1 Flash 1017
none- Cost
- $0.001
- Time
- 7.1s
- Tokens
- 2,012 tok
#293 Nemotron 3 Ultra
none- Cost
- $0.000
- Time
- 149.6s
- Tokens
- 3,405 tok
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 1017 | 5.0 | 10.0 | 0.0% | 0 | 43.95s | 168,815 | 3,381 | 0 | |
| Nemotron 3 Ultra | 5.0 | 10.0 | 0.0% | 0 | 70.17s | 174,213 | 2,074 | 0 |
| 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 1017 | 3.6 | 10.0 | 0.0% | 0 | 1.14s | 552 | 990 | 0 | |
| Nemotron 3 Ultra | 3.5 | 8.0 | 16.7% | 1 | 2.35s | 696 | 239 | 0 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 5.6 | 9.9 | 33.3% | 0 | 2.38s | 7,284 | 3,922 | 0 | |
| Nemotron 3 Ultra | 5.5 | 10.0 | 33.3% | 0 | 1.02s | 7,623 | 369 | 0 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 3.0 | 10.0 | 0.0% | 0 | 7.51s | 99,393 | 7,551 | 0 | |
| Nemotron 3 Ultra | 3.0 | 10.0 | 0.0% | 0 | 21.14s | 73,507 | 7,693 | 0 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 544ms | 7,296 | 201 | 0 | |
| Nemotron 3 Ultra | 10.0 | 10.0 | 100.0% | 0 | 1.94s | 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 V4.1 Flash 1017 | 7.7 | 10.0 | 66.7% | 0 | 463ms | 684 | 30 | 0 | |
| Nemotron 3 Ultra | 5.3 | 10.0 | 33.3% | 0 | 758ms | 682 | 23 | 0 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 5.1 | 3.4 | 33.3% | 1 | 616ms | 474 | 113 | 0 | |
| Nemotron 3 Ultra | 5.0 | 10.0 | 0.0% | 0 | 13.49s | 516 | 101 | 0 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 6.5 | 10.0 | 50.0% | 0 | 608ms | 633 | 60 | 0 | |
| Nemotron 3 Ultra | 10.0 | 10.0 | 100.0% | 0 | 1.46s | 723 | 69 | 0 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 5.4 | 10.0 | 33.3% | 0 | 750ms | 603 | 315 | 0 | |
| Nemotron 3 Ultra | 5.9 | 7.2 | 55.6% | 1 | 1.06s | 726 | 352 | 0 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 1.60s | 8,007 | 228 | 0 | |
| Nemotron 3 Ultra | 10.0 | 10.0 | 100.0% | 0 | 2.99s | 8,544 | 264 | 0 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 3.0 | 10.0 | 0.0% | 0 | 655ms | 186 | 15 | 0 | |
| Nemotron 3 Ultra | 3.0 | 10.0 | 0.0% | 0 | 1.83s | 207 | 111 | 0 |
Quick Compare
Switch Comparison Pair
Nemotron 3 UltranoneFree Availablevsgpt-oss-120bmediumDeepSeek V4.1 Flash 1017nonevsLing 3.0 FlashhighGemini 3.1 Flash LiteminimalvsNemotron 3 UltranoneFree AvailableDeepSeek V4.1 Flash 1017nonevsgpt-oss-120bmediumDeepSeek V4.1 Flash 1017nonevsRing 2.6 1tmediumTrinity Large ThinkinghighvsDeepSeek V4.1 Flash 1017noneNemotron 3 UltranoneFree AvailablevsInkling SmallmediumFree AvailableDeepSeek V4.1 Flash 1017nonevsGPT-5 NanomediumLing 3.0 FlashhighvsNemotron 3 UltranoneFree AvailableDeepSeek V4.1 Flash 1017nonevsGemini 3.1 Flash LiteminimalNemotron 3 UltranoneFree AvailablevsGLM 5.3 FlashXlowRing 2.6 1tmediumvsNemotron 3 UltranoneFree Available