- Rank
- #97
- Total Output Tokens
- 211,310
- Response Time (avg)
- 51.81s
- Total Cost
- $0.042
DeepSeek V4 Flash 0423 (high) vs Gemini 3 Flash Preview (medium)
Gemini 3 Flash Preview (medium) leads on average score with 9.5 vs 7.6. DeepSeek V4 Flash 0423 (high) has the lower benchmark cost at $0.042 vs $0.763. Gemini 3 Flash Preview (medium) is faster at 19.86s vs 51.81s, with pass rates of 69.7% vs 93.9%.
Compared models
- Rank
- #10
- Total Output Tokens
- 239,608
- Response Time (avg)
- 19.86s
- Total Cost
- $0.763
Recommended model
Gemini 3 Flash Preview (medium)
It has the best score here (9.5), while responding about 2.6x faster than DeepSeek V4 Flash 0423 (high).
Detailed comparison
| Metric | DeepSeek V4 Flash 0423 DeepSeek V4 Flash 0423 high | Gemini 3 Flash Preview Gemini 3 Flash Preview medium |
|---|---|---|
| Score | 7.6 | 9.5 |
| Rank | #97 | #10 |
| Reliability | 10.0 | 10.0 |
| Consistency | 8.5 | 9.7 |
| Attempts | 66/66 | 66/66 |
| Tests Correct | ||
| Attempt pass rate | 69.7% | 93.9% |
| Flaky tests | 4 | 1 |
| Total Runs | 66 | 66 |
| Cost per result | 0.446 | 3.814 |
| Total Cost | $0.042 | $0.763 |
| Input Price | $0.089 / 1M | $0.500 / 1M |
| Output Price | $0.178 / 1M | $3.000 / 1M |
| Total Input Tokens | 108,480 | 87,870 |
| Output Tokens | 37,229 | 5,486 |
| Reasoning Tokens | 174,081 | 234,122 |
| Response Time (avg) | 51.81s | 19.86s |
| Response Time (max) | 218.13s | 117.26s |
| Response Time (total) | 1139.75s | 436.88s |
| Parameters | 284B total (13B active) | ~500B total (~20B active) |
| Availability | Open source | Closed |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#97 DeepSeek V4 Flash 0423
high- Cost
- $0.003
- Time
- 93.1s
- Tokens
- 7,926 tok
#10 Gemini 3 Flash Preview
medium- Cost
- $0.010
- Time
- 18.4s
- Tokens
- 3,351 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 Flash 0423 | 8.3 | 10.0 | 75.0% | 0 | 28.51s | 540 | 140 | 7,770 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 3.88s | 494 | 330 | 3,216 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 7.8 | 10.0 | 66.7% | 0 | 50.60s | 7,279 | 395 | 34,862 | |
| Gemini 3 Flash Preview | 8.6 | 7.6 | 88.9% | 1 | 84.40s | 8,122 | 462 | 161,084 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 6.4 | 5.8 | 66.7% | 1 | 104.10s | 82,663 | 4,633 | 37,533 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 26.75s | 63,717 | 3,831 | 23,496 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 10.0 | 10.0 | 100.0% | 0 | 28.03s | 7,290 | 201 | 1,179 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 5.43s | 7,548 | 279 | 4,893 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 3.6 | 7.2 | 22.2% | 1 | 115.42s | 754 | 22,778 | 79,643 | |
| Gemini 3 Flash Preview | 7.7 | 10.0 | 66.7% | 0 | 20.09s | 642 | 12 | 28,642 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 6.1 | 3.1 | 66.7% | 1 | 25.15s | 471 | 79 | 632 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 5.19s | 486 | 72 | 1,905 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 10.0 | 10.0 | 100.0% | 0 | 15.36s | 627 | 63 | 1,622 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 4.04s | 615 | 72 | 2,709 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 8.2 | 7.2 | 88.9% | 1 | 26.11s | 594 | 196 | 1,767 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 4.05s | 558 | 183 | 4,365 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 10.0 | 10.0 | 100.0% | 0 | 74.73s | 8,079 | 228 | 542 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 12.60s | 5,532 | 234 | 1,487 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 3.0 | 10.0 | 0.0% | 0 | 54.46s | 183 | 8,516 | 8,531 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 5.50s | 156 | 11 | 2,325 |
Quick Compare
Switch Comparison Pair
Gemini 3 Flash PreviewmediumvsGPT-6 AstralowClaude Opus 4.6mediumvsDeepSeek V4 Flash 0423highGemini 3 Flash PreviewmediumvsGPT-5.6 SollowSeed-2.0-CodelowvsDeepSeek V4 Flash 0423highDeepSeek V4 Flash 0423highvsGLM 5mediumDeepSeek V4 Flash 0423highvsSolar Pro 4xhighDeepSeek V4 Flash 0423highvsNemotron 3 UltramediumFree AvailableClaude Opus 5nonevsDeepSeek V4 Flash 0423highGemini 3 Flash PreviewmediumvsGPT-5.6 SolhighDeepSeek V4 Flash 0423highvsGPT-5.4 NanomediumClaude Opus 4.8lowvsDeepSeek V4 Flash 0423highSeed-2.0-LitemediumvsDeepSeek V4 Flash 0423high