Step 3.7 Flash
57±0
56interval57
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,310
- Last sync
- 39 min39 minutes ago
All sources syncing normally
- Arena · Text· 5 hours ago
- Arena · WebDev· 5 hours ago
- Arena · Vision· 5 hours ago
- Arena · Agent· 5 hours ago
- GPQA Diamond· 39 minutes ago
- SWE-bench· 39 minutes ago
- Terminal-Bench· 39 minutes ago
- ARC-AGI-2· 39 minutes ago
Filter by org:
Released:
Step 3.5 Flash 2603
56±0
56interval57
step-3.5-flash
52±1
50interval53
One grid, every column. Pick axes in the Axes panel — one axis ranks like a single board, several blend into a weighted composite, all of them read as the index. Rank is assigned before any filter and never renumbers.
| Model | Org | Interval | Swing | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | Add to compare | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 223 | Step 3.7 Flash | stepfun | May 2026 | $0.20 / $1.15 | 56.8 77.2Ranked 56.8 = (1 × 77.2 + 3 × 50) ÷ 4. 77.2 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | — | — | 1/22low | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 77 | — | ||
| 237 | Step 3.5 Flash 2603 | stepfun | — | — | 56.4 75.6Ranked 56.4 = (1 × 75.6 + 3 × 50) ÷ 4. 75.6 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | — | — | 1/22low | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 76 | — | ||
| 373 | step-3.5-flash | stepfun | Feb 2026 | $0.10 / $0.30 | 51.6 53.1Ranked 51.6 = (3 × 53.1 + 3 × 50) ÷ 6. 53.1 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 50–53 | 48 | 3/22 | #111–373 | 60 | — | — | 26 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 73 | — | ||
| 556 | step-3 | stepfun | Oct 2026 | — | 45.7 39.3Ranked 45.7 = (2 × 39.3 + 3 × 50) ÷ 5. 39.3 is the mean percentile over the 2 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 44–48 | 20 | 2/22low | #155–556 | 49 | — | 29 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model