- Rank
- #73
- Total Output Tokens
- 908,171
- Response Time (avg)
- 61.58s
- Total Cost
- $1.204
DeepSeek V4.1 Flash (max) vs Gemini 3.7 Flash (low)
Gemini 3.7 Flash (low) leads on average score with 9.4 vs 8.6. Gemini 3.7 Flash (low) has the lower benchmark cost at $0.183 vs $1.204. Gemini 3.7 Flash (low) is faster at 6.24s vs 61.58s, with pass rates of 69.6% vs 95.7%.
Compared models
- Rank
- #26
- Total Output Tokens
- 38,453
- Response Time (avg)
- 6.24s
- Total Cost
- $0.183
Recommended model
Gemini 3.7 Flash (low)
It has the best score here (9.4), while costing about 6.6x less than DeepSeek V4.1 Flash (max).
Detailed comparison
| Metric | DeepSeek V4.1 Flash DeepSeek V4.1 Flash max | Gemini 3.7 Flash Gemini 3.7 Flash low |
|---|---|---|
| Score | 8.6 | 9.4 |
| Rank | #73 | #26 |
| Reliability | 9.4 | 10.0 |
| Consistency | 9.3 | 9.3 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 69.6% | 95.7% |
| Flaky tests | 2 | 2 |
| Total Runs | 69 | 69 |
| Cost per result | 3.715 | 0.868 |
| Total Cost | $1.204 | $0.183 |
| Input Price | $0.013 / 1M | $0.750 / 1M |
| Output Price | $1.320 / 1M | $3.750 / 1M |
| Cache Read Price | $0.013 / 1M | $0.075 / 1M |
| Cache Write Price | N/A | $0.042 / 1M |
| Total Input Tokens | 414,054 | 188,519 |
| Output Tokens | 7,635 | 7,694 |
| Reasoning Tokens | 900,536 | 30,759 |
| Response Time (avg) | 61.58s | 6.24s |
| Response Time (max) | 335.08s | 58.75s |
| Response Time (total) | 1416.24s | 143.56s |
| Parameters | 748B total (16B active) | ~500B total (~20B active) |
| Availability | Open source | Closed |
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.
#73 DeepSeek V4.1 Flash
max- Cost
- $0.066
- Time
- 211.0s
- Tokens
- 54,712 tok
#26 Gemini 3.7 Flash
low- Cost
- $0.010
- Time
- 23.5s
- Tokens
- 5,210 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 | 10.0 | 10.0 | 100.0% | 0 | 66.63s | 325,030 | 2,077 | 34,968 | |
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 58.75s | 98,197 | 1,400 | 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 | 8.3 | 10.0 | 75.0% | 0 | 4.35s | 852 | 213 | 7,262 | |
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 1.54s | 492 | 99 | 1,398 |
| 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 | 62.50s | 7,509 | 373 | 132,357 | |
| Gemini 3.7 Flash | 7.6 | 7.2 | 77.8% | 1 | 6.20s | 8,118 | 461 | 11,508 |
| 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 | 160.31s | 66,677 | 4,031 | 221,091 | |
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 13.00s | 66,250 | 4,873 | 8,108 |
| 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 | 4.56s | 2,397 | 120 | 2,047 | |
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.15s | 7,548 | 278 | 1,093 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 3.6 | 7.2 | 22.2% | 1 | 198.41s | 909 | 27 | 384,462 | |
| Gemini 3.7 Flash | 8.2 | 7.2 | 88.9% | 1 | 3.09s | 642 | 12 | 3,029 |
| 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 | 4.00s | 549 | 148 | 1,093 | |
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.76s | 486 | 81 | 1,043 |
| 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 | 7.64s | 783 | 63 | 2,293 | |
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.47s | 615 | 72 | 1,778 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 5.5 | 7.1 | 44.4% | 1 | 30.82s | 828 | 339 | 54,014 | |
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 1.92s | 558 | 166 | 1,580 |
| 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 | 9.49s | 8,259 | 228 | 693 | |
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 4.10s | 5,457 | 241 | 160 |
| 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 | 98.48s | 261 | 16 | 60,256 | |
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.92s | 156 | 11 | 1,062 |
Quick Compare
Switch Comparison Pair
Claude Opus 5highvsGemini 3.7 FlashlowClaude Opus 5mediumvsGemini 3.7 FlashlowDeepSeek V4.1 FlashmaxvsMuse Spark 1.1lowClaude Sonnet 5.5highvsDeepSeek V4.1 FlashmaxClaude Opus 5.5highvsGemini 3.7 FlashlowDeepSeek V4.1 FlashmaxvsGPT-6 SollowSeed 2.1 TurbomediumvsDeepSeek V4.1 FlashmaxDeepSeek V4.1 FlashmaxvsMiMo-V2.6-PromediumDeepSeek V4.1 FlashmaxvsQwen3.8 27BhighFree AvailableDeepSeek V4.1 FlashmaxvsGPT-5.2mediumClaude Haiku 5.5lowvsDeepSeek V4.1 FlashmaxDeepSeek V4.1 FlashmaxvsQwen3.8 Max (0902)low