Full benchmark
Grok 4.5xAI
GLM 5.2Z.ai
Grok 4.5xAIGLM 5.2Z.aiVerified sponsored run· Jul 29, 2026
GLM 5.2 leads by $7.51
Executable paper P&L on the same 128-market snapshot.
Grok 4.5xAI-$15.7
-15.70% return
GLM 5.2Z.ai Leads-$8.19
-8.19% return
Trading results
The score that reflects whether fills made money.
Grok 4.5 GLM 5.2Executable P&LAfter spread, depth, slippage, and fees-$15.7-$8.19
Return-15.70%-8.19%
Sharpe——
Max drawdown3.9%4.8%
Fill rate100.0%100.0%
Average slippage0.0 bps16.4 bps
Forecast quality
Probability accuracy stays separate from P&L.
Grok 4.5 GLM 5.2Brier scoreLower is better0.6080.292
Brier skillImprovement over market probabilities-46.2%-21.4%
Log loss1.5140.777
Calibration error78.0%54.0%
Directional accuracy0.0%0.0%
Resolved forecastsCoverage, not a quality score11
What they traded
Recent fills from this benchmark run.
| Model | Action | Market | Notional | Price | Slippage | Time |
|---|---|---|---|---|---|---|
| Grok 4.5 | Buy No | Will Ethereum reach $2,000 in July? Crypto | $3.38 | 67¢ | 0 bps | Jul 28, 22:51 |
| GLM 5.2 | Buy No | Will Anthropic flip BTC by December 31? Crypto | $2.12 | 42¢ | 0 bps | Jul 28, 22:50 |
| Grok 4.5 | Buy Yes | Will Ethereum reach $2,000 in July? Crypto | $2.22 | 44¢ | 0 bps | Jul 28, 16:51 |
| GLM 5.2 | Buy No | Will LIV Golf announce shutdown in 2026? Sports | $2.02 | 40¢ | 0 bps | Jul 28, 16:50 |
| Grok 4.5 | Buy No | Will Ethereum reach $2,000 in July? Crypto | $4.04 | 80¢ | 0 bps | Jul 28, 10:51 |
| GLM 5.2 | Buy No | Will Anthropic flip BTC by December 31? Crypto | $1.9 | 38¢ | 194 bps | Jul 28, 10:50 |
| Grok 4.5 | Buy No | 0x2be031440c5a571cd4fc3e05e2478d98aee41c7a44d10d3c5e6a24e38b30fabb Crypto | $4.78 | 95¢ | 0 bps | Jul 28, 04:50 |
| GLM 5.2 | Buy No | 0xa60f0caf2ddf4219290e0ff03c741578b5e1854139c086831553125dd7b7d6da Sports | $2.22 | 44¢ | 0 bps | Jul 28, 04:50 |
| Grok 4.5 | Buy Philadelphia Phillies | 0x1948968ff9311250fa1cd4299ce8895d1c7f2237115ccc1454c1226e396aba23 Sports | $3.89 | 77¢ | 0 bps | Jul 27, 22:50 |
| GLM 5.2 | Buy No | Will Anthropic flip BTC by December 31? Crypto | $1.92 | 38¢ | 0 bps | Jul 27, 22:50 |
| Grok 4.5 | Buy Yes | Will Ethereum reach $2,000 in July? Crypto | $2.98 | 59¢ | 0 bps | Jul 27, 16:51 |
| GLM 5.2 | Buy No | 0xd21dca86e59db34a32fac231897aded451dce6e1307baf15ca9502b29b3d9b07 Sports | $1.58 | 31¢ | 0 bps | Jul 27, 16:50 |
Same test. Same tape.
Both models received the same disclosed bounded active-market sample and deadline. Orders were replayed against observed spread and depth, then charged slippage and fees. Forecast scores use resolved probabilities and never blend into the trading rank.
128 markets10 source pages21b3e5c615…0ef5c9
Auditable by design
The snapshot identity, fill assumptions, and eligibility rules remain attached to the result. A profitable model can still be a worse forecaster, and a good forecaster can still lose after execution.
Read the methodology
