T3 Code · Performance over time
Turns completed in the window
All metrics
1 / 120
Turns completed in the window (higher is better)
188
18 Nov−1.1% vs the median of up to 7 previous complete nightlies, within noiseFork perf.9 250, +33.0% vs its upstream base
AgentsRange
When upstream merges a fix, the lines meet.
Upstream nightlyPerformance forkNoise bandRange of attempts green = better, red = worse, beyond the noise band
As agents grow.
Agent turns that finished inside the 300 s measurement window, all agents together. Measured only where the level is not saturated: a turn counts when it starts in the window and ends by its close, and at a saturated level turns outlast the window, so there the value is null with the reason not_measured_saturated and agents served is the measure.
Higher is better. Noise band 22.4% on Linux x64 (n = 6), so a change counts beyond 27.4%.
- Unit
- n
- Better
- higher
- Noise band
- 22.4%, threshold 27.4% (n = 6)
- Recorded from
- 17 Oct 2026; before that the series is a gap, never a zero
- Platforms
- Linux x64
- Lane
- Every record, inside the agent ladder
- Upstream builds
- Every upstream build
- Source
result.json:metrics.driver.calls["session.turn"].count
Turns completed in the window (higher is better) at 1 to 250 agents, Linux x64
against
Records, 50 agents
| Date | Tag | Median | Min to max | Valid | vs up to 7 previous | Verdict |
|---|---|---|---|---|---|---|
| 18 Nov 2026 | v0.1.11-nightly.20261118.4903 | 188 | 188 to 189 | 3 | −1.1% | within noise |
| 17 Nov 2026 | v0.1.11-nightly.20261117.4851 | 177 | 169 to 187 | 3 | −7.3% | within noise |
| 16 Nov 2026 | v0.1.10-nightly.20261116.4800 | 191 | 155 to 200 | 3 | −8.0% | within noise |
| 15 Nov 2026 | v0.1.10-nightly.20261115.4749 | 190 | 187 to 191 | 3 | −15.6% | within noise |
| 14 Nov 2026 | v0.1.10-nightly.20261114.4709 | 189 | 142 to 192 | 3 | −16.0% | within noise |
| 13 Nov 2026 | v0.1.10-nightly.20261113.4656 | 140 | 136 to 162 | 3 | −37.8% | regressed beyond noise |
| 12 Nov 2026 | v0.1.10-nightly.20261112.4606 | 207 | 206 to 210 | 3 | −8.0% | within noise |
| 11 Nov 2026 | v0.1.10-nightly.20261111.4544 | 220 | 220 to 231 | 3 | −2.2% | within noise |
| 10 Nov 2026 | v0.1.9-nightly.20261110.4491 | 223 | 222 to 224 | 3 | −0.9% | within noise |
| 9 Nov 2026 | v0.1.9-nightly.20261109.4443 | 224 | 223 to 224 | 3 | −0.4% | within noise |
| 8 Nov 2026 | v0.1.8-nightly.20261108.4380 | 226 | 226 to 231 | 3 | +0.4% | within noise |
| 7 Nov 2026 | v0.1.8-nightly.20261107.4340 | 229 | 227 to 230 | 3 | +1.8% | within noise |
| 6 Nov 2026 | v0.1.8-nightly.20261106.4288 | 227 | 223 to 228 | 3 | +0.9% | within noise |
| 5 Nov 2026 | v0.1.8-nightly.20261105.4234 | 226 | 226 to 227 | 3 | +0.4% | within noise, thin reference |
| 4 Nov 2026 | v0.1.8-nightly.20261104.4192 | 225 | 225 to 226 | 3 | 0.0% | within noise, thin reference |
| 3 Nov 2026 | v0.1.7-nightly.20261103.4138 | 225 | 225 to 226 | 3 | no reference yet | |
| 2 Nov 2026 | v0.1.7-nightly.20261102.4093 | 224 | 221 to 225 | 3 | no reference yet | |
| 1 Nov 2026 | v0.1.7-nightly.20261101.4048 | 222 | 218 to 223 | 3 | no reference yet | |
| 31 Oct 2026 | v0.1.7-nightly.20261031.4004 | 224 | 223 to 224 | 3 | no reference yet | |
| 30 Oct 2026 | v0.1.6-nightly.20261030.3940 | 223 | 223 to 224 | 3 | no reference yet | |
| 29 Oct 2026 | v0.1.6-nightly.20261029.3892 | 217 | 215 to 217 | 3 | no reference yet | |
| 28 Oct 2026 | v0.1.4-nightly.20261028.3841 | 216 | 216 to 217 | 3 | no reference yet | |
| 27 Oct 2026 | v0.1.4-nightly.20261027.3796 | 216 | 215 to 216 | 3 | no reference yet | |
| 26 Oct 2026 | v0.1.3-nightly.20261026.3740 | 214 | 212 to 216 | 3 | no reference yet | |
| 25 Oct 2026 | v0.1.3-nightly.20261025.3682 | 218 | 217 to 221 | 3 | no reference yet | |
| 24 Oct 2026 | v0.1.3-nightly.20261024.3643 | 219 | 216 to 220 | 3 | no reference yet | |
| 23 Oct 2026 | v0.1.3-nightly.20261023.3592 | 217 | 216 to 218 | 3 | no reference yet | |
| 22 Oct 2026 | v0.1.2-nightly.20261022.3541 | 221 | 220 to 221 | 3 | no reference yet | |
| 21 Oct 2026 | v0.1.2-nightly.20261021.3499 | 224 | 223 to 225 | 3 | no reference yet | |
| 20 Oct 2026 | v0.1.1-nightly.20261020.3438 | 222 | 222 to 223 | 3 | no reference yet | |
| 19 Oct 2026 | v0.1.1-nightly.20261019.3373 | 211 | 210 to 214 | 3 | no noise band yet, no verdict | |
| 18 Oct 2026 | v0.1.1-nightly.20261018.3335 | 217 | 215 to 219 | 3 | no noise band yet, no verdict | |
| 17 Oct 2026 | v0.1.1-nightly.20261017.3272 | 216 | 212 to 219 | 3 | no noise band yet, no verdict |
Ladder as a table
| Agents | Nightly 18 Nov | Fork perf.9 |
|---|---|---|
| 1 | 25 | 25 |
| 50 | 188 | 250 |
| 100 | – | 415 |
| 150 | – | 608 |
| 200 | – | 639 |
| 250 | – | 785 |
Download this series
series/linux-x64/turns_completed.latest.jsonlast 90 days, JSON, 26.3 KBseries/linux-x64/turns_completed.all.jsonevery record, JSON, 26.3 KB