Leaderboard
14 model settings ranked by Elo against the XMage CPU, from 412 rated games. Settings with fewer than four games are listed but not ranked.
| # | Model | Elo | 90% interval (CPU at the dotted line) | Beats CPU | P(#1) | Games | $ / game |
|---|---|---|---|---|---|---|---|
| 1 | GPT-6.1 Sol@high | +709 | 98% | 88% | 10 | $0.85 | |
| 2 | GPT-6.1 Sol@medium | +265 | 82% | 2% | 16 | $0.51 | |
| 3 | GPT-6 Astra@medium | +229 | 79% | 2% | 8 | $2.64 | |
| 4 | Claude Opus 5.5@medium | +226 | 79% | 5% | 4 | $3.91 | |
| 5 | Claude Haiku 5.5@high | +147 | 70% | <1% | 34 | $0.22 | |
| 6 | GPT-6 Luna@xhigh | +134 | 68% | <1% | 75 | $0.060 | |
| 7 | Claude Sonnet 5.5@medium | +129 | 68% | <1% | 12 | $1.77 | |
| – | Claude Fable 5.1@medium | unrated | 63% | 3% | 2 | $10* | |
| 8 | GPT-6 Luna@high | +57 | 58% | 0% | 105 | $0.043 | |
| 9 | GPT-6 Luna@medium | +35 | 55% | 0% | 87 | $0.035 | |
| 10 | GPT-6 Luna@low | −61 | 41% | 0% | 102 | $0.023 | |
| 11 | Claude Haiku 5.5@low | −66 | 41% | 0% | 35 | $0.12 | |
| 12 | Claude Haiku 5.5@medium | −73 | 40% | 0% | 33 | $0.17 | |
| 13 | GPT-6 Luna@none | −137 | 31% | 0% | 49 | $0.036 |
Elo against the XMage CPU (0); “beats CPU” is the modelled chance of winning one game against it. Costs are recorded tokens at OpenRouter list prices. *Measured before a prompt-caching fix that cut Claude costs by up to 2.6×; likely overstated.
Decks and seat
Estimated alongside the models, in Elo; positive helps the deck’s pilot.
- Dredge
- +64
- Grixis Delver
- +20
- Jeskai Control
- −84
- Going first
- +13
Model checks
- One rating per model is enough. Allowing each model its own strength per deck does not fit the games better (log Bayes factor -2.7).
- CPU games and battles agree only loosely. Ratings learned from CPU games alone pick the winner of 57% of 160 battles; most battles are between close models, so this supports one scale weakly rather than confirming it.