- Rank
- #47
- Total Output Tokens
- 24,283
- Response Time (avg)
- 6.63s
- Total Cost
- $0.674
Gemini 4 Argon (medium) vs Qwen3.8 Max (0902) (medium)
The average score is effectively tied at 9.0 vs 9.0. Gemini 4 Argon (medium) has the lower benchmark cost at $0.674 vs $1.096. Gemini 4 Argon (medium) is faster at 6.63s vs 30.42s, with pass rates of 84.1% vs 84.1%.
Compared models
- Rank
- #44
- Total Output Tokens
- 92,998
- Response Time (avg)
- 30.42s
- Total Cost
- $1.096
Recommended model
Gemini 4 Argon (medium)
It has the best score here (9.0), while costing about 1.6x less than Qwen3.8 Max (0902) (medium).
Detailed comparison
| Metric | Gemini 4 Argon Gemini 4 Argon medium | Qwen3.8 Max (0902) Qwen3.8 Max (0902) medium |
|---|---|---|
| Score | 9.0 | 9.0 |
| Rank | #47 | #44 |
| Reliability | 10.0 | 10.0 |
| Consistency | 9.6 | 9.3 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 84.1% | 84.1% |
| Flaky tests | 1 | 2 |
| Total Runs | 69 | 69 |
| Cost per result | 3.545 | 6.084 |
| Total Cost | $0.674 | $1.096 |
| Input Price | $2.000 / 1M | $2.000 / 1M |
| Output Price | $10.000 / 1M | $6.000 / 1M |
| Cache Read Price | $0.100 / 1M | $0.250 / 1M |
| Cache Write Price | $0.188 / 1M | $2.500 / 1M |
| Total Input Tokens | 215,326 | 268,540 |
| Output Tokens | 6,668 | 7,499 |
| Reasoning Tokens | 17,615 | 85,499 |
| Response Time (avg) | 6.63s | 30.42s |
| Response Time (max) | 62.49s | 168.09s |
| Response Time (total) | 152.50s | 699.68s |
| Parameters | ~1.2T total (~20B active) | 2.4T total (~100B 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.
#47 Gemini 4 Argon
medium- Cost
- $0.053
- Time
- 43.0s
- Tokens
- 5,348 tok
#44 Qwen3.8 Max (0902)
medium- Cost
- $0.036
- Time
- 108.3s
- Tokens
- 5,980 tok
Category Breakdown
| Agentic | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 62.49s | 121,790 | 1,103 | 8,773 | |
| Qwen3.8 Max (0902) | 10.0 | 10.0 | 100.0% | 0 | 127.50s | 172,217 | 1,538 | 10,782 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 2.29s | 918 | 252 | 595 | |
| Qwen3.8 Max (0902) | 10.0 | 10.0 | 100.0% | 0 | 5.03s | 672 | 295 | 2,003 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 4.86s | 8,448 | 506 | 4,391 | |
| Qwen3.8 Max (0902) | 8.4 | 7.4 | 88.9% | 1 | 45.74s | 7,893 | 551 | 20,628 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 4 Argon | 6.4 | 5.8 | 66.7% | 1 | 15.06s | 65,297 | 3,623 | 2,875 | |
| Qwen3.8 Max (0902) | 10.0 | 10.0 | 100.0% | 0 | 94.38s | 68,852 | 3,895 | 24,303 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 2.39s | 8,025 | 340 | 101 | |
| Qwen3.8 Max (0902) | 10.0 | 10.0 | 100.0% | 0 | 10.54s | 7,782 | 261 | 2,591 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 4 Argon | 5.3 | 10.0 | 33.3% | 0 | 2.44s | 963 | 51 | 636 | |
| Qwen3.8 Max (0902) | 3.6 | 7.2 | 22.2% | 1 | 49.45s | 780 | 44 | 19,572 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 2.40s | 591 | 136 | 0 | |
| Qwen3.8 Max (0902) | 10.0 | 10.0 | 100.0% | 0 | 7.56s | 516 | 202 | 689 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 2.71s | 825 | 98 | 198 | |
| Qwen3.8 Max (0902) | 10.0 | 10.0 | 100.0% | 0 | 4.24s | 699 | 90 | 886 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 2.10s | 882 | 231 | 46 | |
| Qwen3.8 Max (0902) | 10.0 | 10.0 | 100.0% | 0 | 5.89s | 696 | 353 | 1,599 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 4 Argon | 9.8 | 10.0 | 100.0% | 0 | 8.01s | 7,326 | 304 | 0 | |
| Qwen3.8 Max (0902) | 10.0 | 10.0 | 100.0% | 0 | 5.93s | 8,229 | 249 | 194 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 4 Argon | 3.0 | 10.0 | 0.0% | 0 | 1.91s | 261 | 24 | 0 | |
| Qwen3.8 Max (0902) | 3.0 | 10.0 | 0.0% | 0 | 17.01s | 204 | 21 | 2,252 |
Quick Compare
Switch Comparison Pair
Claude Opus 5lowvsGemini 4 ArgonmediumGemini 4 ArgonmediumvsGLM 5.3 FlashmaxGemini 3.5 FlashlowvsQwen3.8 Max (0902)mediumGemini 3.5 Flash LitehighvsQwen3.8 Max (0902)mediumClaude Opus 5lowvsQwen3.8 Max (0902)mediumGemini 4 ArgonmediumvsMuse Spark 1.2highGemini 3.6 FlashlowvsQwen3.8 Max (0902)mediumQwen3.8 Max (0902)mediumvsGLM 5.3 FlashmaxMuse WonderminimalvsQwen3.8 Max (0902)mediumSeed 2.1 TurbohighvsQwen3.8 Max (0902)mediumQwen3.8 Max (0902)mediumvsParetodefaultMuse WonderlowvsQwen3.8 Max (0902)medium