Board contestants
21 cards · each averaged across the boards it contested
One row per consolidated card, ordered by OVR. Deliberately unnumbered: these means span different sets of boards, so a place in this list would be the cross-workflow ranking the leaderboard refuses to publish.
| Model | OVR | GRD | ADH | SYN | PRC | EFF | CON | Archetype | Range |
|---|---|---|---|---|---|---|---|---|---|
| gemini-3-6-flash | 93 | 99 | 98 | 99 | 94 | 79 | 86 | Sniper | 84–993 of 5 boards |
| gpt-5-6-terra | 90 | 94 | 90 | 89 | 90 | 85 | 92 | Sniper | 83–984 of 5 boards |
| deepseek-v4-pro | 88 | 96 | 90 | 96 | 88 | 74 | 89 | Sniper | 84–964 of 5 boards |
| grok-4-5 | 88 | 99 | 90 | 99 | 97 | 49 | 94 | Sniper | 73–984 of 5 boards |
| deepseek-v4-flash | 86 | 96 | 90 | 96 | 89 | 57 | 87 | Sniper | 75–924 of 5 boards |
| qwen-3-7-max | 84 | 95 | 87 | 99 | 90 | 61 | 78 | Playmaker | 75–944 of 5 boards |
| gpt-5-6-luna | 82 | 87 | 92 | 90 | 93 | 56 | 80 | Anchor | 68–935 of 5 boards |
| mimo-2-5-pro | 82 | 93 | 89 | 87 | 83 | 67 | 74 | Sniper | 65–984 of 5 boards |
| deepseek-v4-flash-vision | 81 | 94 | 99 | 99 | 60 | 24 | 96 | Anchor | 81–811 of 5 boards |
| gemini-3-5-flash | 78 | 84 | 88 | 89 | 94 | 33 | 83 | Anchor | 61–954 of 5 boards |
| kimi-2-7 | 78 | 90 | 88 | 72 | 82 | 66 | 66 | Sniper | 68–984 of 5 boards |
| glm-5-3-flash | 78 | 89 | 99 | 99 | 70 | 18 | 86 | Anchor | 78–781 of 5 boards |
| hunyuan-3 | 76 | 93 | 87 | 81 | 80 | 32 | 78 | Sniper | 69–824 of 5 boards |
| claude-sonnet-5 | 75 | 86 | 81 | 99 | 86 | 57 | 47 | Playmaker | 62–814 of 5 boards |
| glm-5-2 | 75 | 85 | 88 | 74 | 79 | 60 | 71 | Anchor | 64–854 of 5 boards |
| step-3-7-flash | 74 | 83 | 86 | 76 | 88 | 54 | 66 | Anchor | 68–814 of 5 boards |
| doubao-seed-2-1-pro | 73 | 86 | 88 | 87 | 88 | 34 | 60 | Anchor | 66–804 of 5 boards |
| longcat-2-0 | 72 | 84 | 84 | 87 | 87 | 29 | 68 | Playmaker | 46–834 of 5 boards |
| mimo-2-5 | 70 | 80 | 90 | 74 | 84 | 65 | 32 | Anchor | 62–794 of 5 boards |
| gemini-3-7-flash | 67 | 59 | 99 | 99 | 64 | 8 | 92 | Anchor | 67–671 of 5 boards |
| minimax-m3 | 64 | 78 | 80 | 60 | 72 | 42 | 50 | Anchor | 42–924 of 5 boards |
No model matches .
Provisional
23 cards · measured, never ranked · grouped by model
Runs measured outside a contested field. An ability card is an absolute measurement — passed/total per axis, EFF against each workflow's own par — so it stays meaningful with no opponent. A rank does not: with no field, a first place measures nothing. Nothing here carries one, and nothing here reaches the leaderboard.
| Model | OVR | GRD | ADH | SYN | PRC | EFF | CON | Archetype | Range |
|---|---|---|---|---|---|---|---|---|---|
| deepseek-v4-proRun #104 | 82 | 93 | 89 | 84 | 93 | 60 | 72 | Sniper | 61–994 workflows · 2 trials |
| gpt-5-6-lunaRun #129 max | 84 | 91 | 94 | 95 | 90 | 47 | 89 | Playmaker | 73–985 workflows · 2 trials |
| gpt-5-6-lunaRun #130 low | 78 | 81 | 91 | 83 | 87 | 67 | 67 | Anchor | 49–965 workflows · 2 trials |
| glm-5-3-flashRun #131 max | 79 | 85 | 92 | 95 | 88 | 25 | — | Playmaker | 69–935 workflows · 1 trial |
| hunyuan-3Run #129 xhigh | 80 | 88 | 93 | 77 | 82 | 78 | 50 | Anchor | 54–915 workflows |
| hunyuan-3Run #130 low | 79 | 89 | 89 | 79 | 85 | 63 | 63 | Sniper | 61–915 workflows |
| mimo-2-5Run #129 high | 70 | 77 | 80 | 81 | 82 | 63 | 52 | Anchor | 54–795 workflows · 2 trials |
| mimo-2-5Run #130 low | 76 | 82 | 82 | 79 | 81 | 71 | 70 | Sniper | 49–985 workflows |
| gemini-3-7-flashRun #113 | 91 | 99 | 96 | 99 | 96 | 60 | — | Sniper | 87–985 workflows · 1 trial |
| gemini-3-7-flashRun #129 xhigh | 83 | 95 | 92 | 99 | 92 | 31 | 89 | Playmaker | 77–965 workflows · 2 trials |
| gemini-3-7-flashRun #130 low | 86 | 84 | 94 | 99 | 91 | 76 | 86 | Playmaker | 73–985 workflows · 2 trials |
| minimax-m3Run #129 max | 72 | 79 | 86 | 79 | 82 | 55 | 58 | Anchor | 52–935 workflows · 2 trials |
| minimax-m3Run #130 low | 77 | 80 | 88 | 87 | 80 | 56 | 79 | Anchor | 61–985 workflows · 2 trials |
| gemini-3-8-flashRun #138 low | 86 | 91 | 92 | 99 | 94 | 47 | — | Playmaker | 71–986 workflows · 1 trial |
| gemini-3-8-flashRun #134 xhigh | 79 | 91 | 97 | 99 | 95 | 4 | 89 | Playmaker | 71–846 workflows |
| grok-4-6Run #104 | 81 | 96 | 90 | 99 | 98 | 21 | 86 | Playmaker | 74–914 workflows · 2 trials |
| glm-5-3Run #115 | 87 | 93 | 92 | 95 | 91 | 58 | — | Playmaker | 69–995 workflows · 1 trial |
| glm-5-3Run #132 max | 87 | 90 | 91 | 95 | 90 | 64 | — | Playmaker | 72–995 workflows · 1 trial |
| qwen-3-8-flashRun #131 max | 78 | 88 | 85 | 99 | 88 | 20 | — | Playmaker | 63–905 workflows · 1 trial |
| qwen-3-8-27bRun #129 max | 84 | 91 | 86 | 99 | 89 | 58 | 87 | Playmaker | 75–945 workflows · 2 trials |
| qwen-3-8-27bRun #130 low | 81 | 88 | 84 | 79 | 81 | 76 | 80 | Sniper | 53–955 workflows · 2 trials |
| deepseek-v4-flash-dsRun #129 max | 81 | 91 | 91 | 97 | 88 | 54 | 69 | Playmaker | 67–895 workflows · 2 trials |
| deepseek-v4-flash-dsRun #130 low | 84 | 91 | 88 | 95 | 90 | 61 | 86 | Playmaker | 73–925 workflows · 2 trials |
No model matches .