- Rank
- #15
- Total Output Tokens
- 252,536
- Response Time (avg)
- 21.57s
- Total Cost
- $0.876
Gemini 3 Flash Preview (medium) vs Gemini 4 Argon (high)
The average score is effectively tied at 9.6 vs 9.5. Gemini 3 Flash Preview (medium) has the lower benchmark cost at $0.876 vs $1.802. Gemini 4 Argon (high) is faster at 19.03s vs 21.57s, with pass rates of 94.2% vs 97.1%.
Compared models
- Rank
- #17
- Total Output Tokens
- 132,073
- Response Time (avg)
- 19.03s
- Total Cost
- $1.802
Recommended model
Gemini 3 Flash Preview (medium)
It has the best score here (9.6), while costing about 2.1x less than Gemini 4 Argon (high).
Detailed comparison
| Metric | Gemini 3 Flash Preview Gemini 3 Flash Preview medium | Gemini 4 Argon Gemini 4 Argon high |
|---|---|---|
| Score | 9.6 | 9.5 |
| Rank | #15 | #17 |
| Reliability | 10.0 | 9.9 |
| Consistency | 9.7 | 9.3 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 94.2% | 97.1% |
| Flaky tests | 1 | 2 |
| Total Runs | 69 | 69 |
| Cost per result | 4.169 | 8.578 |
| Total Cost | $0.876 | $1.802 |
| Input Price | $0.500 / 1M | $2.000 / 1M |
| Output Price | $3.000 / 1M | $10.000 / 1M |
| Cache Read Price | $0.050 / 1M | $0.100 / 1M |
| Cache Write Price | $0.084 / 1M | $0.188 / 1M |
| Total Input Tokens | 235,726 | 240,264 |
| Output Tokens | 6,669 | 5,707 |
| Reasoning Tokens | 245,867 | 126,366 |
| Response Time (avg) | 21.57s | 19.03s |
| Response Time (max) | 117.26s | 82.53s |
| Response Time (total) | 496.12s | 437.77s |
| Parameters | ~500B total (~20B active) | ~1.2T total (~20B active) |
| Availability | Closed | 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.
#15 Gemini 3 Flash Preview
medium- Cost
- $0.010
- Time
- 18.4s
- Tokens
- 3,351 tok
#17 Gemini 4 Argon
high- Cost
- $0.173
- Time
- 141.5s
- Tokens
- 17,366 tok
Category Breakdown
| Agentic | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 59.24s | 147,856 | 1,183 | 11,745 | |
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 82.53s | 162,601 | 1,058 | 16,544 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 3.88s | 494 | 330 | 3,216 | |
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 3.98s | 918 | 155 | 3,556 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 8.6 | 7.6 | 88.9% | 1 | 84.40s | 8,122 | 462 | 161,084 | |
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 15.81s | 8,448 | 489 | 20,751 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 26.75s | 63,717 | 3,831 | 23,496 | |
| Gemini 4 Argon | 7.3 | 5.8 | 83.3% | 1 | 56.32s | 50,219 | 2,878 | 32,994 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 5.43s | 7,548 | 279 | 4,893 | |
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 8.04s | 8,025 | 338 | 5,519 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 7.7 | 10.0 | 66.7% | 0 | 20.09s | 642 | 12 | 28,642 | |
| Gemini 4 Argon | 8.2 | 7.2 | 88.9% | 1 | 32.86s | 963 | 49 | 29,490 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 5.19s | 486 | 72 | 1,905 | |
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 6.44s | 591 | 127 | 1,572 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 4.04s | 615 | 72 | 2,709 | |
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 5.32s | 825 | 96 | 2,992 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 4.05s | 558 | 183 | 4,365 | |
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 4.46s | 882 | 220 | 2,859 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 12.60s | 5,532 | 234 | 1,487 | |
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 28.47s | 6,531 | 273 | 8,505 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 5.50s | 156 | 11 | 2,325 | |
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 5.66s | 261 | 24 | 1,584 |
Quick Compare
Switch Comparison Pair
Gemini 3 Flash PreviewmediumvsGPT-6.1 SollowGemini 3 Flash PreviewmediumvsGPT-6 AstralowGemini 4 ArgonhighvsGPT-6.1 SollowGemini 4 ArgonhighvsGPT-6 AstralowGemini 3 Flash PreviewmediumvsGPT-5.6 SollowGemini 4 ArgonhighvsGPT-6 SolmediumGemini 4 ArgonhighvsGPT-5.6 SolmediumGemini 4 ArgonhighvsGPT-5.6 SollowGemini 4 ArgonhighvsGPT-6 AstramediumGemini 3 Flash PreviewmediumvsGPT-6.1 SolhighGemini 3 Flash PreviewmediumvsGPT-5.6 SolhighGemini 4 ArgonhighvsGPT-5.5low