- Rank
- #50
- Total Output Tokens
- 96,502
- Response Time (avg)
- 24.81s
- Total Cost
- $2.006
GPT-5.4 (medium) vs GPT-5.5 (medium)
GPT-5.5 (medium) leads on average score with 9.2 vs 8.8. GPT-5.4 (medium) has the lower benchmark cost at $2.006 vs $4.809. GPT-5.4 (medium) is faster at 24.81s vs 39.86s, with pass rates of 78.3% vs 88.4%.
Compared models
- Rank
- #30
- Total Output Tokens
- 130,107
- Response Time (avg)
- 39.86s
- Total Cost
- $4.809
Recommended model
GPT-5.4 (medium)
Its score stays close to the best score here (8.8 vs 9.2), while costing about 2.4x less than GPT-5.5 (medium).
Detailed comparison
| Metric | GPT-5.4 GPT-5.4 medium | GPT-5.5 GPT-5.5 medium |
|---|---|---|
| Score | 8.8 | 9.2 |
| Rank | #50 | #30 |
| Reliability | 10.0 | 10.0 |
| Consistency | 8.7 | 9.0 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 78.3% | 88.4% |
| Flaky tests | 4 | 3 |
| Total Runs | 69 | 69 |
| Cost per result | 12.535 | 25.306 |
| Total Cost | $2.006 | $4.809 |
| Input Price | $2.500 / 1M | $5.000 / 1M |
| Output Price | $15.000 / 1M | $30.000 / 1M |
| Total Input Tokens | 223,210 | 180,959 |
| Output Tokens | 7,312 | 6,472 |
| Reasoning Tokens | 89,190 | 123,635 |
| Response Time (avg) | 24.81s | 39.86s |
| Response Time (max) | 100.41s | 332.10s |
| Response Time (total) | 570.60s | 916.82s |
| Parameters | ~1.5T total (~100B active) | ~1.5T total (~100B active) |
| Availability | Closed | Closed |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#50 GPT-5.4
medium- Cost
- $0.214
- Time
- 199.6s
- Tokens
- 14,349 tok
#30 GPT-5.5
medium- Cost
- $0.112
- Time
- 71.9s
- Tokens
- 3,807 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
Quick Compare
Switch Comparison Pair
Claude Sonnet 5.5maxvsGPT-5.5mediumGPT-5.4mediumvsQwen3.8 MAXlowDeepSeek V4.1 FlashhighvsGPT-5.4mediumGPT-5.5mediumvsQwen3.8 Max (0902)highMuse Spark 1.2lowvsGPT-5.4mediumMuse Spark 1.3highvsGPT-5.5mediumSeed 2.1 TurbolowvsGPT-5.5mediumGPT-5.5mediumvsParetononeSeed 2.1 TurbohighvsGPT-5.5mediumMuse Spark 1.2highvsGPT-5.4mediumGPT-5.4mediumvsQwen3.8 27BhighFree AvailableGemini 3.5 FlashlowvsGPT-5.5medium