| Area / family | Inst. | Fable 5.1 | Opus 5.5 | Sonnet 5.5 | GPT-6.1 Sol | Gemini 4 Argon | Grok 4.7 |
|---|---|---|---|---|---|---|---|
| 13 | 23 | 21 | 17 | 20 | 20 | 10 | |
| 9 | 47 | 42 | 36 | 41 | 40 | 25 | |
| 13 | 75 | 71 | 65 | 69 | 69 | 54 | |
| 6 | 78 | 73 | 66 | 71 | 70 | 50 | |
| 11 | 84 | 80 | 74 | 79 | 78 | 60 |
| # | Model | Full completion | Items solved | pass^3 | Steps / trial | Cost / trial |
|---|---|---|---|---|---|---|
| 01 | Claude Fable 5.1Anthropic | 19.1 12.9–26.1 | 59.4 | 3/52 | 408 | $162.35 |
| 02 | Claude Opus 5.5Anthropic | 15.1 9.7–21.6 | 55.4 | 2/52 | 419 | $66.70 |
| 05 | Claude Sonnet 5.5Anthropic | 10.3 6.4–15.5 | 49.8 | 1/52 | 452 | $35.98 |
| 03 | GPT-6.1 SolOpenAI | 13.9 9.0–20.1 | 54.1 | 1/52 | 430 | $34.23 |
| 04 | Gemini 4 ArgonGoogle | 13.3 8.7–19.3 | 53.5 | 1/52 | 430 | $34.23 |
| 06 | Grok 4.7xAI | 4.5 1.3–8.3 | 38.7 | 0/52 | 551 | $25.66 |
| 07 | Kimi 2.6Moonshot | 0.7 0.3–1.8 | 26.5 | 0/52 | 579 | $15.36 |
| 08 | MiniMax M3MiniMax | 0.7 0.3–1.8 | 26.6 | 0/52 | 579 | $6.18 |
| 09 | Qwen 3.7-PlusAlibaba | 0.6 0.3–1.7 | 26.0 | 0/52 | 579 | $6.60 |
| Model | Harness | Full completion | Items solved | pass^3 | Steps / trial | Cost / trial |
|---|---|---|---|---|---|---|
| Claude Fable 5.1 | H1 | 19.1 | 59.4 | 3/52 | 408 | $162.35 |
| Claude Fable 5.1 | H5 | 24.7 | 64.1 | 4/52 | 367 | $178.59 |
| Claude Opus 5.5 | H1 | 15.1 | 55.4 | 2/52 | 419 | $66.70 |
| Claude Opus 5.5 | H5 | 20.2 | 60.3 | 3/52 | 377 | $73.37 |
| Claude Sonnet 5.5 | H1 | 10.3 | 49.8 | 1/52 | 452 | $35.98 |
| Claude Sonnet 5.5 | H5 | 14.6 | 54.9 | 2/52 | 407 | $39.58 |
| GPT-6.1 Sol | H1 | 13.9 | 54.1 | 1/52 | 430 | $34.23 |
| GPT-6.1 Sol | H5 | 18.9 | 59.1 | 3/52 | 387 | $37.65 |
| Gemini 4 Argon | H1 | 13.3 | 53.5 | 1/52 | 430 | $34.23 |
| Gemini 4 Argon | H5 | 18.2 | 58.5 | 3/52 | 387 | $37.65 |
| Grok 4.7 | H1 | 4.5 | 38.7 | 0/52 | 551 | $25.66 |
| Grok 4.7 | H2 | 3.2 | 36.9 | 0/52 | 551 | $25.66 |
| Grok 4.7 | H3 | 1.3 | 30.1 | 0/52 | 551 | $25.66 |
| Grok 4.7 | H4 | 5.6 | 42.3 | 0/52 | 551 | $25.66 |
| Model | Full completion | Items solved |
|---|---|---|
| Claude Fable 5.1 | 6.4 | 51.9 |
| Claude Opus 5.5 | 4.0 | 46.7 |
| Claude Sonnet 5.5 | 1.9 | 39.6 |
| GPT-6.1 Sol | 3.4 | 45.0 |
| Gemini 4 Argon | 3.2 | 44.2 |
| Grok 4.7 | 0.0 | 26.4 |
| Kimi 2.6 | 0.0 | 15.6 |
| MiniMax M3 | 0.0 | 15.7 |
| Qwen 3.7-Plus | 0.0 | 15.2 |
| Model | Full completion | Cost / trial | One pass over 52 | Cost per full completion |
|---|---|---|---|---|
| Claude Fable 5.1 | 19.1 | $162.35 | $8,442 | $848 |
| Claude Opus 5.5 | 15.1 | $66.70 | $3,468 | $443 |
| Claude Sonnet 5.5 | 10.3 | $35.98 | $1,871 | $351 |
| GPT-6.1 Sol | 13.9 | $34.23 | $1,780 | $247 |
| Gemini 4 Argon | 13.3 | $34.23 | $1,780 | $257 |
| Grok 4.7 | 4.5 | $25.66 | $1,334 | $570 |
| Kimi 2.6 | 0.7 | $15.36 | $799 | — |
| MiniMax M3 | 0.7 | $6.18 | $322 | — |
| Qwen 3.7-Plus | 0.6 | $6.60 | $343 | — |
{
"ticket": 48213,
"comment": "cmt_48213_10",
"body": "The card network accepted the fraud dispute in full, and the $1,349.99 credit on your account is now final."
}{
"comment": "cmt_48213_10",
"posted": true,
"ledger": {
"txn_0002": {
"NETWORK_SETTLEMENT": null
}
}
}