- Rank
- #248
- Total Output Tokens
- 273,780
- Response Time (avg)
- 14.85s
- Total Cost
- $0.185
DeepSeek V4.1 Flash vs Nemotron 3.5 Lightning (high)
Nemotron 3.5 Lightning (high) leads on average score with 5.6 vs 5.4. Nemotron 3.5 Lightning (high) has the lower benchmark cost at $0.134 vs $0.185. DeepSeek V4.1 Flash is faster at 14.85s vs 58.26s, with pass rates of 34.9% vs 50.0%.
Compared models
- Rank
- #241
- Total Output Tokens
- 654,597
- Response Time (avg)
- 58.26s
- Total Cost
- $0.134
Recommended model
DeepSeek V4.1 Flash
Its score stays close to the best score here (5.4 vs 5.6), while responding about 3.9x faster than Nemotron 3.5 Lightning (high).
Detailed comparison
| Metric | DeepSeek V4.1 Flash DeepSeek V4.1 Flash none | Nemotron 3.5 Lightning Nemotron 3.5 Lightning high Free Available |
|---|---|---|
| Score | 5.4 | 5.6 |
| Rank | #248 | #241 |
| Reliability | 9.6 | 9.9 |
| Consistency | 9.3 | 5.6 |
| Attempts | 66/66 | 66/66 |
| Tests Correct | ||
| Attempt pass rate | 34.9% | 50.0% |
| Flaky tests | 2 | 12 |
| Total Runs | 66 | 66 |
| Cost per result | 2.642 | 0.000 |
| Total Cost | $0.185 | $0.134 |
| Input Price | $0.150 / 1M | $0.080 / 1M |
| Output Price | $0.600 / 1M | $0.200 / 1M |
| Total Input Tokens | 137,687 | 118,016 |
| Output Tokens | 273,780 | 148,344 |
| Reasoning Tokens | 0 | 506,253 |
| Response Time (avg) | 14.85s | 58.26s |
| Response Time (max) | 247.66s | 285.26s |
| Response Time (total) | 326.72s | 1281.79s |
| Parameters | 748B total (16B active) | 30B total (3B 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.
#248 DeepSeek V4.1 Flash
none- Cost
- $0.021
- Time
- 55.4s
- Tokens
- 17,181 tok
#241 Nemotron 3.5 Lightning
high- Cost
- $0.000
- Time
- 92.8s
- Tokens
- 11,343 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 V4.1 Flash | 3.7 | 8.4 | 8.3% | 1 | 1.90s | 552 | 907 | 0 | |
| Nemotron 3.5 Lightning | 5.5 | 3.7 | 66.7% | 3 | 10.29s | 696 | 2,432 | 15,948 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 5.5 | 10.0 | 33.3% | 0 | 83.66s | 7,284 | 263,438 | 0 | |
| Nemotron 3.5 Lightning | 4.4 | 5.1 | 33.3% | 2 | 168.41s | 7,623 | 68,533 | 242,319 |
| Combined | 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 | 10.37s | 116,933 | 8,699 | 0 | |
| Nemotron 3.5 Lightning | 6.4 | 10.0 | 50.0% | 0 | 160.45s | 90,257 | 17,550 | 119,725 |
| 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 | 3.09s | 2,322 | 117 | 0 | |
| Nemotron 3.5 Lightning | 7.3 | 5.9 | 83.3% | 1 | 13.99s | 7,944 | 3,210 | 16,835 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 7.7 | 10.0 | 66.7% | 0 | 5.46s | 684 | 21 | 0 | |
| Nemotron 3.5 Lightning | 2.9 | 4.4 | 22.2% | 2 | 88.61s | 798 | 45,616 | 72,496 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 5.5 | 10.0 | 0.0% | 0 | 1.69s | 474 | 93 | 0 | |
| Nemotron 3.5 Lightning | 3.7 | 9.5 | 0.0% | 0 | 7.58s | 516 | 4,331 | 4,408 |
| Instructions following | 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 | 6.81s | 633 | 62 | 0 | |
| Nemotron 3.5 Lightning | 8.5 | 6.8 | 83.3% | 1 | 4.98s | 723 | 502 | 3,779 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 5.3 | 7.2 | 44.4% | 1 | 1.49s | 603 | 215 | 0 | |
| Nemotron 3.5 Lightning | 3.6 | 1.8 | 44.4% | 3 | 6.09s | 726 | 1,236 | 9,851 |
| 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 | 3.76s | 8,016 | 219 | 0 | |
| Nemotron 3.5 Lightning | 10.0 | 10.0 | 100.0% | 0 | 6.92s | 8,526 | 3,745 | 3,781 |
| 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 | 1.32s | 186 | 9 | 0 | |
| Nemotron 3.5 Lightning | 3.0 | 10.0 | 0.0% | 0 | 77.98s | 207 | 1,189 | 17,111 |
Quick Compare
Switch Comparison Pair
Nemotron 3.5 LightninghighFree AvailablevsHy4 previewlowKAT-Coder-Air V2.5mediumvsNemotron 3.5 LightninghighFree AvailableNemotron 3.5 LightninghighFree AvailablevsQwen3.6 27BnoneDeepSeek V4.1 FlashnonevsLaguna S 2.1mediumFree AvailableGemma 4 26B A4BnoneFree AvailablevsNemotron 3.5 LightninghighFree AvailableNemotron 3.5 LightninghighFree AvailablevsQwen3.8 27BnoneDeepSeek V4.1 FlashnonevsKAT-Coder-Air V2.5lowDeepSeek V4.1 FlashnonevsLaguna S 2.1highFree AvailableNemotron 3.5 LightninghighFree AvailablevsQwen3.5-122B-A10BnoneDeepSeek V4.1 FlashnonevsHy4 previewlowKimi K2.6nonevsNemotron 3.5 LightninghighFree AvailableDeepSeek V4 Flash 0423nonevsNemotron 3.5 LightninghighFree Available