Atlas

Benchmarks

TCSExam constructions

GitHub

TCSExam's construction track: 20 tasks that build an object such as a code or a circuit, graded against a task reference. 100% matches the reference and scores above it beat it, so the scale has no upper bound.

Models
8
Top score
104.9
Leader
GPT-6 Astra
Updated
Nov 5, 2026
Resolution
—
Saturation
—
Signal
92ndpercentile
205 benchmarks from 0.8 to 3.6219 benchmarks from 3.6 to 6.4134 benchmarks from 6.4 to 9.393 benchmarks from 9.3 to 12.155 benchmarks from 12.1 to 14.925 benchmarks from 14.9 to 17.713 benchmarks from 17.7 to 20.55 benchmarks from 20.5 to 23.37 benchmarks from 23.3 to 26.27 benchmarks from 26.2 to 29.01 benchmark from 29.0 to 31.83 benchmarks from 31.8 to 34.66 benchmarks from 34.6 to 37.43 benchmarks from 37.4 to 40.21 benchmark from 40.2 to 43.11 benchmark from 45.9 to 48.71 benchmark from 65.6 to 68.4

61st strongest of 779

Signal-to-noise +16.16 for the TCSExam family

Difficulty
Not estimated

This benchmark has no declared score range, so it cannot be placed on the 0-1 scale the capability curve requires.

8 dated models · 3 frontier modelsClosed weightsOpen weights
Data: Moonshot AIatlas.village.dev
#ModelSettingScoreSource
1GPT-6 Astramax · Codex
104.9
TCSExam paper Table 2 (Full, GPT-6 Astra)
2Kimi K3.1 Promax · Kimi Code
98.6
TCSExam paper Table 2 (Full, Kimi K3.1 Pro)
3GLM-5.3max · Claude Code
97.7
TCSExam paper Table 2 (Full, GLM-5.3)
4Kimi K3max · Kimi Code
95.5
TCSExam paper Table 2 (Full, Kimi K3)
5Qwen3.8 Max (0902)max · Claude Code
95.1
TCSExam paper Table 2 (Full, Qwen3.8 Max (0902))
6DeepSeek V4.1 Flash 1017max · Claude Code
91.8
TCSExam paper Table 2 (Full, DeepSeek V4.1 Flash 1017)
7DeepSeek V4.1 Flashmax · Claude Code
86.6
TCSExam paper Table 2 (Full, DeepSeek V4.1 Flash 0910)
8Grok 4.6x-high · Grok Build
86.2
TCSExam paper Table 2 (Full, Grok 4.6)
Loading Atlas data…