Same evidence. Independent predictions. Results tracked before and after kickoff.
Consensus spread across 11 sportsbooks and how far each line has moved this week. Five-model picks post about two hours before each kickoff.
| Kickoff (ET) | Matchup | Spread | Moved | Total | Five-model picks |
|---|---|---|---|---|---|
| Sun 9:30 AM | Texans at Jaguars | Jaguars -2.5 (books -2 to -2.5) | — | 42.5 | About 2 h before kickoff |
| Sun 1:00 PM | Bears at Falcons | Bears -1 (books +0.5 to -1.5) | 2 toward Falcons | 52 | About 2 h before kickoff |
| Sun 1:00 PM | Ravens at Browns | Ravens -4 (books -3.5 to -4) | 0.5 toward Browns | 41 | About 2 h before kickoff |
| Sun 1:00 PM | Titans at Colts | Colts -7 (books -6.5 to -7) | — | 44.5 | About 2 h before kickoff |
| Sun 1:00 PM | Jets at Patriots | Patriots -7 (books -7 to -7.5) | — | 43.5 | About 2 h before kickoff |
| Sun 1:00 PM | Saints at Giants | Saints -0.5 (books +1 to -1.5) | — | 46 | About 2 h before kickoff |
| Sun 1:00 PM | Panthers at Eagles | Panthers -3.5 | 4.5 toward Panthers | 39 | About 2 h before kickoff |
| Sun 1:00 PM | Steelers at Buccaneers | Steelers -2.5 (books -2 to -2.5) | 0.5 toward Buccaneers | 39.5 | About 2 h before kickoff |
| Sun 4:05 PM | Cardinals at Rams | Rams -12.5 (books -12 to -13) | 0.5 toward Cardinals | 51.5 | About 2 h before kickoff |
| Sun 4:25 PM | Chargers at Chiefs | Chiefs -8 (books -7.5 to -9) | 0.5 toward Chargers | 41.5 | About 2 h before kickoff |
| Sun 4:25 PM | Bills at Raiders | Bills -4.5 (books -4.5 to -5.5) | 1.5 toward Raiders | 53.5 | About 2 h before kickoff |
| Sun 8:20 PM | Cowboys at Packers | Packers -1 (books -1 to -1.5) | — | 53 | About 2 h before kickoff |
| Mon 8:15 PM | Commanders at 49ers | 49ers -7.5 (books -7.5 to -8) | — | 51.5 | About 2 h before kickoff |
No model finished above .500 against the contest line; Claude Fable 5.1 led at 7–8. Favorites won 9–5 outright but went 7–7 against the sportsbook spread.
| Model | Contest line | Sportsbook spread | Outright winners |
|---|---|---|---|
| Claude Fable 5.1 | 7–8 | 7–7 (1 push) | 8–6 |
| DeepSeek V4 Pro 0813 | 7–8 | 6–8 (1 push) | 7–7 |
| GPT-6 Astra | 6–9 | 5–9 (1 push) | 7–7 |
| Gemini 3.8 Flash | 5–10 | 7–7 (1 push) | 8–6 |
| Grok 4.6 | 3–12 | 4–10 (1 push) | 9–5 |
Records use each model's first pregame pick at the saved line. One week is a small sample.
Winner ≠ spread. Each has its own rank and record. Cards ordered by outright winners · Season through Week 6. Live records show where picks stand at the current score; season records count final results only.
51 correct · 21 incorrect now
1 tiedSeason final: 51W · 21L · 1T70.8% win rate
35 correct · 38 incorrect now
0 pushesSeason final: 35W · 38L · 0P47.9% win rate
35 correct · 34 incorrect now
4 pushesSeason final: 35W · 34L · 4P50.7% win rate
Awaiting pregame selection
Season final: 0W · 4L · 0 void0.0% win rate
49 correct · 23 incorrect now
1 tiedSeason final: 49W · 23L · 1T68.1% win rate
41 correct · 32 incorrect now
0 pushesSeason final: 41W · 32L · 0P56.2% win rate
36 correct · 33 incorrect now
4 pushesSeason final: 36W · 33L · 4P52.2% win rate
Awaiting pregame selection
Season final: 0W · 4L · 0 void0.0% win rate
46 correct · 26 incorrect now
1 tiedSeason final: 46W · 26L · 1T63.9% win rate
41 correct · 32 incorrect now
0 pushesSeason final: 41W · 32L · 0P56.2% win rate
34 correct · 35 incorrect now
4 pushesSeason final: 34W · 35L · 4P49.3% win rate
Awaiting pregame selection
Season final: 1W · 3L · 0 void25.0% win rate
45 correct · 27 incorrect now
1 tiedSeason final: 45W · 27L · 1T62.5% win rate
31 correct · 42 incorrect now
0 pushesSeason final: 31W · 42L · 0P42.5% win rate
33 correct · 36 incorrect now
4 pushesSeason final: 33W · 36L · 4P47.8% win rate
Awaiting pregame selection
Season final: 0W · 4L · 0 void0.0% win rate
44 correct · 28 incorrect now
1 tiedSeason final: 44W · 28L · 1T61.1% win rate
35 correct · 38 incorrect now
0 pushesSeason final: 35W · 38L · 0P47.9% win rate
32 correct · 37 incorrect now
4 pushesSeason final: 32W · 37L · 4P46.4% win rate
Awaiting pregame selection
Season final: 0W · 4L · 0 void0.0% win rate
Provisional comparison on 1 shared games this week. Season records stay within nfl-evidence-v1; W = wins, L = losses, T = ties, P = pushes. Scheduled games are not counted as winning or losing. A live lead is not a final win or a win probability.
Seahawks: Chazz Surratt (LB) out
Oct 14, 9:42 PM ETPaste into Claude Web or Codex Web for winners, both spread choices, score totals and an optional three-game parlay. Includes every scheduled day. Independent web reviews are separate from the controlled model comparison.
Winner = who wins the game. Spread = who covers the handicap. Winners below come from each model’s saved predicted score, not a separate moneyline analysis. Week 6 spread agreement uses the contest line when supplied. Agreement is not a measured chance of winning.
| Game / kickoff / actual scoreSeason through Week 6 · Ordered by Outright winners | Grok 4.6 51 correct · 21 incorrect now 1 tiedSeason final: 51W · 21L · 1T70.8% win rate 35 correct · 38 incorrect now 0 pushesSeason final: 35W · 38L · 0P47.9% win rate 35 correct · 34 incorrect now 4 pushesSeason final: 35W · 34L · 4P50.7% win rate Awaiting pregame selection Season final: 0W · 4L · 0 void0.0% win rate | Claude Fable 5.1 49 correct · 23 incorrect now 1 tiedSeason final: 49W · 23L · 1T68.1% win rate 41 correct · 32 incorrect now 0 pushesSeason final: 41W · 32L · 0P56.2% win rate 36 correct · 33 incorrect now 4 pushesSeason final: 36W · 33L · 4P52.2% win rate Awaiting pregame selection Season final: 0W · 4L · 0 void0.0% win rate | GPT-6 Astra 46 correct · 26 incorrect now 1 tiedSeason final: 46W · 26L · 1T63.9% win rate 41 correct · 32 incorrect now 0 pushesSeason final: 41W · 32L · 0P56.2% win rate 34 correct · 35 incorrect now 4 pushesSeason final: 34W · 35L · 4P49.3% win rate Awaiting pregame selection Season final: 1W · 3L · 0 void25.0% win rate | Gemini 3.8 Flash 45 correct · 27 incorrect now 1 tiedSeason final: 45W · 27L · 1T62.5% win rate 31 correct · 42 incorrect now 0 pushesSeason final: 31W · 42L · 0P42.5% win rate 33 correct · 36 incorrect now 4 pushesSeason final: 33W · 36L · 4P47.8% win rate Awaiting pregame selection Season final: 0W · 4L · 0 void0.0% win rate | DeepSeek V4 Pro 0813 44 correct · 28 incorrect now 1 tiedSeason final: 44W · 28L · 1T61.1% win rate 35 correct · 38 incorrect now 0 pushesSeason final: 35W · 38L · 0P47.9% win rate 32 correct · 37 incorrect now 4 pushesSeason final: 32W · 37L · 4P46.4% win rate Awaiting pregame selection Season final: 0W · 4L · 0 void0.0% win rate |
|---|---|---|---|---|---|
Seahawks @ Broncos4/5 models agreeGroup contest: Seahawks -2.5Oct 15, 8:15 PM ETScores loading… |
Most wins: Grok 4.61 wins · 0 losses · 100.0% win rate
| Rank | Model | Wins | Losses | Ties | Win rate | Final | Pending | No pick |
|---|---|---|---|---|---|---|---|---|
| 1 | Grok 4.6 | 1 | 0 | 0 | 100.0% | 1 | 0 | 0 |
| 2 | Claude Fable 5.1 | 0 | 1 | 0 | 0.0% | 1 | 0 | 0 |
| 2 | DeepSeek V4 Pro 0813 | 0 | 1 | 0 | 0.0% | 1 | 0 | 0 |
| 2 | Gemini 3.8 Flash | 0 | 1 | 0 | 0.0% | 1 | 0 | 0 |
| 2 | GPT-6 Astra | 0 | 1 | 0 | 0.0% | 1 | 0 | 0 |
Same games, same prompt: 1 shared forecasts per model. Ranked by wins, then win rate; equal scores share a rank. Win rate excludes ties and pushes.
Outright choices come from saved score estimates. A predicted tie is “No pick”; no moneyline profit is inferred. Week 1 is a small sample, not evidence of consistent skill.
Seahawks @ BroncosOct 15, 8:15 PM ET
Claude Fable 5.1Winner: SeahawksFrom predicted score · LOSS
Spread: Seahawks -2.5
Contest: Seahawks -2.5
Predicted score: SEA 23 – DEN 17
Spread result: loss
Quote: DraftKings -115
Oct 15, 6:14 PM ETNews impact: The confirmed absences of Surtain and Hufanga (plus Moss questionable) materially weaken Denver's pass defense, the unit that has been carrying a stagnant offense, and raise Seattle's offensive ceiling via JSN against backup corners. Seattle's own absences (Charbonnet, Price, two LBs) hurt its run game and run defense depth but are already reflected in its recent form. Darnold and JSN are listed without designations, removing the main Seattle availability question. Weather (55F, light gusts, 20% precipitation) is not a factor. All of this was published before the quoted line, so it does not establish an edge; a single DraftKings snapshot does not show movement, and active/inactive lists are not confirmed in the packet.
Reasoning & counterargument: Denver enters this short-week home game without its two best defensive backs: CB Pat Surtain II (ankle) and S Talanoa Hufanga (ankle) are both ruled out, and CB Riley Moss (ribs) is questionable, leaving a man-coverage-heavy secondary exposed to Jaxon Smith-Njigba, who practiced fully and carries no designation. Denver's offense is also described as badly limited: 31st in 20+ yard plays, Bo Nix the league's most conservative downfield thrower coming off his worst game, Sean Payton retaking playcalling after four games, and last week's 23-17 win over the Chargers leaning on short fields. Seattle's defense ranks near the top against short passing and explosive plays and leads the league in takeaways (11), which fits poorly for a dink-and-dunk Denver attack. That profile supports Seattle -2.5 as the forced-choice side, and the same team at the identical contest handicap of Denver +2.5. Strongest counterargument: Seattle is a defending champion that is nonetheless 25th in EPA and 26th in efficiency, with Sam Darnold throwing five interceptions in three games, both top running backs (Price, Charbonnet) out, two linebackers (Surratt, Thomas) out, and a road game at altitude on a short week after a tight divisional loss. Denver's aggressive pass rush can target Darnold's poor pressured-dropback numbers, and in a 40.5-total game the margin is compressed, making a 1-3 point Seattle win (which loses -2.5) quite plausible. The injury news is public and already in the line; no proven edge exists, so this is a forced opinion, not a bet recommendation.
Sources: injuries Seahawks-Broncos on TNF Week 6: Highlights, TDs, key plays How to bet Seahawks-Broncos: Analysis, tips and top prop plays Is Seahawks OC Brian Fleury a 'home run' hire? How the rookie playcaller is faring The Odds API matchup
Recorded: Oct 15, 6:15 PM ET
Original betting assessment: Pass — no wager recommended. This separate assessment does not cancel the model’s prediction.
Served by Anthropic. Cost: $0.2545.
Input SHA-256: 1925f63121789a42170fd66b599a4e2c10893723df8b93d04598718ac9da510a
Each model chooses one locked ticket from the same fresh pregame slate once at least three shared games are eligible. Outright moneylines and sportsbook spreads may be mixed; contest lines are excluded. One lost leg loses the ticket. Pushes drop out; three pushes void it. Earlier weeks count final tickets only; live parlay ranks count a ticket as on track only after all three legs have started with no leg behind. Each ticket counts once, separately from its three legs.
Model selections for tracking. No wager is placed and no combined payout is quoted; leg prices may come from different books. Waiting for at least three shared, fresh pregame packets. No selections have been invented.
| Prompt | Week | Model | Winner W–L–T | Winner win rate | Spread W–L–P | Pending | ATS / 95% interval | Paper units | ROI | Contest W–L–P | Contest win rate | Total error | API errors |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| nfl-evidence-v1 | 1 | DeepSeek V4 Pro 0813 | 10–4–00 pending · 0 no pick | 71.4% | 6–8–0 | 0 | 42.9%21.4%–67.4% | -2.56 | -18.3% | 6–8–0 | 42.9% | 10.50 | 3 |
| nfl-evidence-v1 | Season | DeepSeek V4 Pro 0813 | 44–28–10 pending · 0 no pick | 61.1% | 32–37–4 | 0 | 46.4%35.1%–58.0% | -7.97 | -10.9% | 35–38–0 | 47.9% | 10.25 | 15 |
| nfl-evidence-v1 | 1 | GPT-6 Astra | 11–3–00 pending · 0 no pick | 78.6% | 6–8–0 | 0 | 42.9%21.4%–67.4% | -2.64 | -18.9% | 9–5–0 | 64.3% | 10.71 | 0 |
| nfl-evidence-v1 | Season | GPT-6 Astra | 48–29–10 pending · 0 no pick | 62.3% | 37–37–4 | 0 | 50.0%38.9%–61.1% | -3.91 | -5.0% | 44–34–0 | 56.4% | 9.92 | 0 |
| nfl-evidence-v1 | 1 | Claude Fable 5.1 | 11–3–00 pending · 0 no pick | 78.6% | 7–7–0 | 0 | 50.0%26.8%–73.2% | -0.67 | -4.8% | 9–5–0 | 64.3% | 10.64 | 8 |
| nfl-evidence-v1 | Season | Claude Fable 5.1 | 50–27–10 pending · 0 no pick | 64.9% | 40–34–4 | 0 | 54.1%42.8%–64.9% | +2.13 | 2.7% | 45–33–0 | 57.7% | 10.04 | 10 |
| nfl-evidence-v1 | 1 | Gemini 3.8 Flash | 11–3–00 pending · 0 no pick | 78.6% | 7–7–0 | 0 | 50.0%26.8%–73.2% | -0.67 | -4.8% | 7–7–0 | 50.0% | 11.86 | 3 |
| nfl-evidence-v1 | Season | Gemini 3.8 Flash | 47–29–10 pending · 0 no pick | 61.8% | 36–37–4 | 0 | 49.3%38.2%–60.5% | -4.67 | -6.1% | 33–44–0 | 42.9% | 10.25 | 8 |
| nfl-evidence-v1 | 1 | Grok 4.6 | 11–3–00 pending · 0 no pick | 78.6% | 6–8–0 | 0 | 42.9%21.4%–67.4% | -2.6 | -18.6% | 7–7–0 | 50.0% | 12.86 | 0 |
| nfl-evidence-v1 | Season | Grok 4.6 | 53–24–10 pending · 0 no pick | 68.8% | 38–36–4 | 0 | 51.4%40.2%–62.4% | -1.59 | -2.0% | 39–39–0 | 50.0% | 10.41 | 0 |
| nfl-evidence-v1 | 2 | DeepSeek V4 Pro 0813 | 8–3–00 pending · 0 no pick | 72.7% | 4–7–0 | 0 | 36.4%15.2%–64.6% | -3.5 | -31.8% | 4–7–0 | 36.4% | 10.55 | 11 |
| nfl-evidence-v1 | 2 | GPT-6 Astra | 10–6–00 pending · 0 no pick | 62.5% | 8–8–0 | 0 | 50.0%28.0%–72.0% | -1 | -6.2% | 8–8–0 | 50.0% | 10.56 | 0 |
| nfl-evidence-v1 | 2 | Claude Fable 5.1 | 9–7–00 pending · 0 no pick | 56.3% | 7–9–0 | 0 | 43.8%23.1%–66.8% | -2.71 | -16.9% | 7–9–0 | 43.8% | 10.13 | 2 |
| nfl-evidence-v1 | 2 | Gemini 3.8 Flash | 8–7–00 pending · 0 no pick | 53.3% | 5–10–0 | 0 | 33.3%15.2%–58.3% | -5.61 | -37.4% | 4–11–0 | 26.7% | 9.47 | 5 |
| nfl-evidence-v1 | 2 | Grok 4.6 | 10–6–00 pending · 0 no pick | 62.5% | 6–10–0 | 0 | 37.5%18.5%–61.4% | -4.63 | -28.9% | 7–9–0 | 43.8% | 10.13 | 0 |
| nfl-evidence-v1 | 3 | DeepSeek V4 Pro 0813 | 10–6–00 pending · 0 no pick | 62.5% | 10–5–1 | 0 | 66.7%41.7%–84.8% | +4.03 | 25.2% | 10–6–0 | 62.5% | 10.44 | 0 |
| nfl-evidence-v1 | 3 | GPT-6 Astra | 10–6–00 pending · 0 no pick | 62.5% | 11–4–1 | 0 | 73.3%48.0%–89.1% | +5.88 | 36.8% | 11–5–0 | 68.8% | 10.75 | 0 |
| nfl-evidence-v1 | 3 | Claude Fable 5.1 | 10–6–00 pending · 0 no pick | 62.5% | 12–3–1 | 0 | 80.0%54.8%–93.0% | +7.75 | 48.4% | 11–5–0 | 68.8% | 11.06 | 0 |
| nfl-evidence-v1 | 3 | Gemini 3.8 Flash | 10–6–00 pending · 0 no pick | 62.5% | 12–3–1 | 0 | 80.0%54.8%–93.0% | +7.75 | 48.4% | 9–7–0 | 56.3% | 11.50 | 0 |
| nfl-evidence-v1 | 3 | Grok 4.6 | 10–6–00 pending · 0 no pick | 62.5% | 12–3–1 | 0 | 80.0%54.8%–93.0% | +7.79 | 48.7% | 10–6–0 | 62.5% | 10.44 | 0 |
| nfl-evidence-v1 | 4 | DeepSeek V4 Pro 0813 | 9–7–00 pending · 0 no pick | 56.3% | 6–8–2 | 0 | 42.9%21.4%–67.4% | -2.42 | -15.1% | 8–8–0 | 50.0% | 9.56 | 0 |
| nfl-evidence-v1 | 4 | GPT-6 Astra | 10–6–00 pending · 0 no pick | 62.5% | 7–7–2 | 0 | 50.0%26.8%–73.2% | -0.66 | -4.1% | 10–6–0 | 62.5% | 8.44 | 0 |
| nfl-evidence-v1 | 4 | Claude Fable 5.1 | 12–4–00 pending · 0 no pick | 75.0% | 7–7–2 | 0 | 50.0%26.8%–73.2% | -0.55 | -3.5% | 11–5–0 | 68.8% | 8.63 | 0 |
| nfl-evidence-v1 | 4 | Gemini 3.8 Flash | 10–6–00 pending · 0 no pick | 62.5% | 5–9–2 | 0 | 35.7%16.3%–61.2% | -4.48 | -28.0% | 8–8–0 | 50.0% | 9.44 | 0 |
| nfl-evidence-v1 | 4 | Grok 4.6 | 12–4–00 pending · 0 no pick | 75.0% | 9–5–2 | 0 | 64.3%38.8%–83.7% | +3.22 | 20.1% | 11–5–0 | 68.8% | 9.25 | 0 |
| nfl-evidence-v1 | 5 | DeepSeek V4 Pro 0813 | 7–7–10 pending · 0 no pick | 50.0% | 6–8–1 | 0 | 42.9%21.4%–67.4% | -2.53 | -16.9% | 7–8–0 | 46.7% | 10.20 | 1 |
| nfl-evidence-v1 | 5 | GPT-6 Astra | 7–7–10 pending · 0 no pick | 50.0% | 5–9–1 | 0 | 35.7%16.3%–61.2% | -4.49 | -30.0% | 6–9–0 | 40.0% | 9.07 | 0 |
| nfl-evidence-v1 | 5 | Claude Fable 5.1 | 8–6–10 pending · 0 no pick | 57.1% | 7–7–1 | 0 | 50.0%26.8%–73.2% | -0.69 | -4.6% | 7–8–0 | 46.7% | 9.87 | 0 |
| nfl-evidence-v1 | 5 | Gemini 3.8 Flash | 8–6–10 pending · 0 no pick | 57.1% | 7–7–1 | 0 | 50.0%26.8%–73.2% | -0.66 | -4.4% | 5–10–0 | 33.3% | 9.33 | 0 |
| nfl-evidence-v1 | 5 | Grok 4.6 | 9–5–10 pending · 0 no pick | 64.3% | 4–10–1 | 0 | 28.6%11.7%–54.6% | -6.33 | -42.2% | 3–12–0 | 20.0% | 9.93 | 0 |
| nfl-evidence-v1 | 6 | DeepSeek V4 Pro 0813 | 0–1–00 pending · 0 no pick | 0.0% | 0–1–0 | 0 | 0.0%0.0%–79.3% | -1 | -100.0% | 0–1–0 | 0.0% | 12.00 | 0 |
| nfl-evidence-v1 | 6 | GPT-6 Astra | 0–1–00 pending · 0 no pick | 0.0% | 0–1–0 | 0 | 0.0%0.0%–79.3% | -1 | -100.0% | 0–1–0 | 0.0% | 12.00 | 0 |
| nfl-evidence-v1 | 6 | Claude Fable 5.1 | 0–1–00 pending · 0 no pick | 0.0% | 0–1–0 | 0 | 0.0%0.0%–79.3% | -1 | -100.0% | 0–1–0 | 0.0% | 9.00 | 0 |
| nfl-evidence-v1 | 6 | Gemini 3.8 Flash | 0–1–00 pending · 0 no pick | 0.0% | 0–1–0 | 0 | 0.0%0.0%–79.3% | -1 | -100.0% | 0–1–0 | 0.0% | 6.00 | 0 |
| nfl-evidence-v1 | 6 | Grok 4.6 | 1–0–00 pending · 0 no pick | 100.0% | 1–0–0 | 0 | 100.0%20.7%–100.0% | +0.95 | 95.2% | 1–0–0 | 100.0% | 6.00 | 0 |
First valid forecast per model, game and prompt version, recorded before kickoff. A later forecast cannot replace an earlier result. Final scores come from ESPN. Spread picks use the saved handicap and American price. Pushes refund the stake and are excluded from ATS hit rate; they remain settled exposures for paper ROI. All recorded picks count in the prediction benchmark. The original prompt also asked whether the model recommended wagering; that separate assessment is preserved in the audit trail and does not remove a prediction from scoring. Contest choices are graded without an invented price. Outright winners are derived from the saved score estimates and graded separately; a tied final game is a tie, while a tied or missing predicted score produces no winner pick. Winner win rate excludes ties and no-picks. A missing contest choice is not a loss.
The leaderboard includes only games where every listed model has an eligible forecast on the same packet. The detailed history includes all eligible forecasts and can have unequal coverage. Season totals stay within the selected prompt version. Prior results are not automatically fed into future prompts. Score error is mean absolute error per team. Total error measures the combined points estimate. The descriptive 95% interval uses the Wilson method; games and predictions can be correlated. Small samples cannot establish consistent skill. More model agreement does not mean a higher win probability.
This first Week 1 run includes the 14 remaining games and excludes the two previously completed games. Future packets are collected in the two hours before kickoff. Models receive the same prompt and evidence for each game, with high reasoning and a 16,384-token output ceiling. Source collection failures and model failures are retained in the audit. A new prompt version starts a separate comparison group.