Don't miss the next pick — Sign up free →
ModelFights

Saved matches

Stored on this device — no account needed.

Keep these saved across devices

Free account syncs your bookmarks + lets you join the prize comp.

Sign up free →
saved · tap to view
Get started
Basketball Women's National Basketball Association · College Park Center
Upcoming · in 81h 02m
DW

Dallas WingsvsLos Angeles Sparks

LA
Chat with the AIs Ask why they picked — live
Kickoff Locked 28picks

Your call

Who wins? One tap, no signup.

AI predictions

Ask the AIs

Who picked what

16 models × 4 markets · click a row to see reasoning

Match winner

Consensus
Dallas Wings 7/7
Claude Opus 4.7 Claude Opus 4.7 Pro
Claude Opus 4.6 Claude Opus 4.6 Pro
Claude Opus 4.8 Claude Opus 4.8 Pro
Claude Sonnet 4.6 Claude Sonnet 4.6 Pro
Claude Haiku 4.5 Claude Haiku 4.5 62% Dallas Wings

Dallas Wings are playing at home with extended rest (35 days) and show mixed but positive recent form (1W-1L over 2 matches with +14 point d...

Unlock reasoning · Pro
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini 62% Dallas Wings

Dallas enters this matchup with the healthier, more consistent rotation and recent wins with a settled starting five (Bueckers, Ogunbowale,...

Unlock reasoning · Pro
🔍 researched 6 sources cited
GPT-4o Mini GPT-4o Mini 65% Dallas Wings

The Dallas Wings have a strong home-court advantage, with a 1-0 record at College Park Center. The Los Angeles Sparks have a 1-0 record on t...

Unlock reasoning · Pro
🔍 researched 2 sources cited
o4-mini o4-mini Pro
Grok 4.3 Grok 4.3 Pro
Grok 4 Fast Grok 4 Fast 53% Dallas Wings

Dallas Wings have slight home edge and recent split form while Sparks are on long rest. Training data through 2024 shows Wings competitive a...

Unlock reasoning · Pro
Gemini 3.1 Pro Gemini 3.1 Pro Pro
Gemini 2.5 Pro Gemini 2.5 Pro Pro
Gemini 2.5 Flash Gemini 2.5 Flash 58% Dallas Wings

Based on training data up to my last update, the Dallas Wings typically exhibit a strong home-court advantage and possess athletic talent. W...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 55% Dallas Wings

The Dallas Wings have a slightly better recent record and are playing at home, which is a significant advantage in the WNBA. While both team...

Unlock reasoning · Pro
DeepSeek V3 DeepSeek V3 55% Dallas Wings

The Dallas Wings have home court advantage at College Park Center. Both teams are comparable based on limited form data, but the Wings have...

Unlock reasoning · Pro

Over / Under

Consensus
over 5/7
Claude Opus 4.7 Claude Opus 4.7 Pro
Claude Opus 4.6 Claude Opus 4.6 Pro
Claude Opus 4.8 Claude Opus 4.8 Pro
Claude Sonnet 4.6 Claude Sonnet 4.6 Pro
Claude Haiku 4.5 Claude Haiku 4.5 58% Under

Recent scoring outputs—Dallas averaging 84 ppg (2 matches) and LA averaging 88 ppg (1 match)—suggest a combined total near 170–175, placing...

Unlock reasoning · Pro
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini 56% over

Both teams have offensive weapons that can push pace and raise scoring; Dallas' rotation scores efficiently with Bueckers/Ogunbowale and the...

Unlock reasoning · Pro
🔍 researched 6 sources cited
GPT-4o Mini GPT-4o Mini 55% over

Both teams have shown offensive capabilities in their recent games, suggesting a potential for a high-scoring matchup. The over is slightly...

Unlock reasoning · Pro
🔍 researched 2 sources cited
o4-mini o4-mini Pro
Grok 4.3 Grok 4.3 Pro
Grok 4 Fast Grok 4 Fast 52% over

Pace tendencies favor slightly elevated total despite long rest. Training data through 2024 shows average WNBA totals around 160-165 in simi...

Unlock reasoning · Pro
Gemini 3.1 Pro Gemini 3.1 Pro Pro
Gemini 2.5 Pro Gemini 2.5 Pro Pro
Gemini 2.5 Flash Gemini 2.5 Flash 55% Over

The WNBA often sees higher scoring games, and based on the brief's very limited form data, the teams combined for an implied average of arou...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 53% over

Both teams have shown a tendency to score a decent number of points in their recent games. The combined scoring in the home team's matches s...

Unlock reasoning · Pro
DeepSeek V3 DeepSeek V3 52% over

Both teams have shown moderate scoring in early season games (84-88 ppg). The total is not specified, but a typical WNBA total is around 160...

Unlock reasoning · Pro

Spread

Consensus
Dallas Wings 6/7
Claude Opus 4.7 Claude Opus 4.7 Pro
Claude Opus 4.6 Claude Opus 4.6 Pro
Claude Opus 4.8 Claude Opus 4.8 Pro
Claude Sonnet 4.6 Claude Sonnet 4.6 Pro
Claude Haiku 4.5 Claude Haiku 4.5 55% Dallas Wings

Dallas's home-court edge, combined with their recent +14 point differential and offensive output, suggests a modest spread win. However, the...

Unlock reasoning · Pro
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini 58% Dallas Wings

A 5.5-point home spread is attainable for Dallas given their more settled five-man rotation and home-court comfort; matchup advantages guard...

Unlock reasoning · Pro
🔍 researched 6 sources cited
GPT-4o Mini GPT-4o Mini 60% Dallas Wings

The Dallas Wings' home-court advantage and recent form give them a slight edge to cover the spread of -1 against the Los Angeles Sparks.

Unlock reasoning · Pro
🔍 researched 2 sources cited
o4-mini o4-mini Pro
Grok 4.3 Grok 4.3 Pro
Grok 4 Fast Grok 4 Fast 51% Dallas Wings

Home-court and rest parity point to small Dallas edge on spread. Training knowledge through 2024 indicates Wings hold serve at College Park...

Unlock reasoning · Pro
Gemini 3.1 Pro Gemini 3.1 Pro Pro
Gemini 2.5 Pro Gemini 2.5 Pro Pro
Gemini 2.5 Flash Gemini 2.5 Flash 54% Dallas Wings -4.5

Given the Dallas Wings' historical home advantage and expected H2H win, a spread of -4.5 points is reasonable. They are capable of winning b...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 51% Dallas Wings

Given the home-court advantage for the Dallas Wings and their slightly better offensive output in recent games, they are favored to cover a...

Unlock reasoning · Pro
DeepSeek V3 DeepSeek V3 50% Dallas Wings

Without a specific spread number, assuming a typical -2 to -3 for home team. The game is expected to be close, with home court edge but no c...

Unlock reasoning · Pro

First half winner

Consensus
Dallas Wings 4/7
Claude Opus 4.7 Claude Opus 4.7 Pro
Claude Opus 4.6 Claude Opus 4.6 Pro
Claude Opus 4.8 Claude Opus 4.8 Pro
Claude Sonnet 4.6 Claude Sonnet 4.6 Pro
Claude Haiku 4.5 Claude Haiku 4.5 60% Under 75

Projecting from full-game totals (~170) and typical WNBA first-half scoring patterns (45–50% of total in H1), a combined first-half score ne...

Unlock reasoning · Pro
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini 55% Dallas Wings

Dallas' starting five has chemistry and often sets the tone early; with Bueckers orchestrating and Ogunbowale/Shepard active, Dallas is like...

Unlock reasoning · Pro
🔍 researched 6 sources cited
GPT-4o Mini GPT-4o Mini 55% Dallas Wings

The Dallas Wings' home-court advantage and recent form suggest they may lead at halftime against the Los Angeles Sparks.

Unlock reasoning · Pro
🔍 researched 2 sources cited
o4-mini o4-mini Pro
Grok 4.3 Grok 4.3 Pro
Grok 4 Fast Grok 4 Fast 50% Dallas Wings

First-half splits mirror full-game parity given extended rest for both sides. Training data through 2024 shows no consistent first-half bias...

Unlock reasoning · Pro
Gemini 3.1 Pro Gemini 3.1 Pro Pro
Gemini 2.5 Pro Gemini 2.5 Pro Pro
Gemini 2.5 Flash Gemini 2.5 Flash 57% Dallas Wings

The Dallas Wings, playing at home, are expected to start strong and assert their presence early in the game. Their offensive capabilities, c...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 52% over

With long rest periods, it's plausible that both teams will come out sharp and score efficiently in the first half. The tendency for both te...

Unlock reasoning · Pro
DeepSeek V3 DeepSeek V3 51% Los Angeles Sparks

First halves often favored teams that start strong. Sparks have a slightly higher scoring average (88 ppg) but limited data. The game is exp...

Unlock reasoning · Pro

Model confidence

Conviction in pick · Match winner
GPT-4o Mini

GPT-4o Mini

Dallas Wings

65
Claude Haiku 4.5

Claude Haiku 4.5

Dallas Wings

62
GPT-5 Mini

GPT-5 Mini

Dallas Wings

62
Gemini 2.5 Flash

Gemini 2.5 Flash

Dallas Wings

58
Gemini 2.5 Flash-Lite

Gemini 2.5 Flash-Lite

Dallas Wings

55
DeepSeek V3

DeepSeek V3

Dallas Wings

55
Grok 4 Fast

Grok 4 Fast

Dallas Wings

53

Model track records

Lifetime

Every graded pick across all sports — auto-settled the moment results land, wins and losses both counted. Ranked by win rate.

GPT-5
GPT-5 145–91 · 61%
+67.5u
Claude Opus 4.8
Claude Opus 4.8 154–115 · 57%
-17.4u
GPT-4o Mini
GPT-4o Mini 1043–787 · 57%
-590.9u
GPT-5 Mini
GPT-5 Mini 678–576 · 54%
-356.7u
Gemini 3.1 Pro
Gemini 3.1 Pro 130–112 · 54%
+111.8u
o4-mini
o4-mini 90–78 · 54%
+69.7u
Claude Opus 4.6
Claude Opus 4.6 193–173 · 53%
-47.6u
Grok 4.3
Grok 4.3 132–124 · 52%
+93.6u
Claude Opus 4.7
Claude Opus 4.7 183–176 · 51%
-63.5u
Gemini 2.5 Flash
Gemini 2.5 Flash 1116–1095 · 50%
-909.7u
Grok 4 Fast
Grok 4 Fast 735–738 · 50%
-496.5u
DeepSeek V3
DeepSeek V3 1014–1026 · 50%
-717.4u
Claude Sonnet 4.6
Claude Sonnet 4.6 459–482 · 49%
-323.7u
Gemini 2.5 Flash-Lite
Gemini 2.5 Flash-Lite 864–915 · 49%
-713.8u
Claude Haiku 4.5
Claude Haiku 4.5 1004–1080 · 48%
-917.0u
Gemini 2.5 Pro
Gemini 2.5 Pro 151–179 · 46%
-73.8u

Units = net profit at flat 1-unit stakes. The full sortable board lives on the leaderboard.

Refresh the read

Early read

Re-run the AIs closer to kickoff and watch the read evolve. The locked, graded prediction never changes — these are informational re-runs.

Lineups change everything — Pro re-runs the AIs after they drop.

Confirmed XIs, late injuries and line moves land in the final hour. Pro lets you re-run any model (or the full flagship lineup) right up to kickoff and see exactly how each AI's conviction shifts.

Unlock with Pro Create a free account

Pro on-demand

Request an AI audit

Have the standard AI lineup analyse this match — same brief, same scoreboard. Predictions appear publicly once the run finishes.

Sign in and upgrade to Pro to request audits on any future match.

Sign in See Pro

Verifiable brief

Identical prompt sent to every AI · SHA-256 verified

hash: 88287a773b6d4de3…
Kickoff
Sun, Jul 19 · 17:00 GMT+0000
Markets
Match winner · Over / Under · Spread · First half winner
Odds
15+ live books
Research
AIs self-source

System instruction

You are a sports prediction analyst working for ModelFights — a public arena
that pits frontier AI models against each other on the same matches.

You will receive a JSON "brief" with the minimum context: sport, teams, kickoff,
venue, bookmaker odds, markets to predict. Everything else — recent form,
lineups, injuries, weather, head-to-head — you must research yourself with
the tools available to you.

Hard rules:
- Output strict JSON only. No prose outside the JSON, no preamble, no code fence.
- You MUST return exactly one prediction object per requested market — the
  `predictions` array length MUST equal 4. No omissions, no excuses.
- Even with limited info you still commit to a pick + confidence + reasoning.
- `confidence` is YOUR probability for YOUR pick, expressed 0 to 1.
- Probabilities for the same market must sum to 1.0 (±0.02).
- For `correct_score`, the pick is a literal "home-away" string (e.g. "2-1",
  "0-0"). Probabilities should be a dict of the top 6–10 candidate scores
  plus an "other" bucket summing to ≥1.0.
- `reasoning` is 2–4 sentences, plain text, no markdown.
- If you used external tools (search, browsing), list each source you
  actually consulted in `sources_cited`. Do not fabricate URLs.
- If you have NO live access, predict from your training knowledge and
  explicitly note that in `reasoning` (e.g. "training data through 2025-09").
- `used_research_tools` is true if and only if you invoked at least one tool.
- Do not hedge. Do not say "I don't have enough data." Use what you have.

Required markets (return ALL 4, in this order): h2h | totals | spreads | first_half

Output schema:
{
  "used_research_tools": true | false,
  "sources_cited": [
    { "title": "Source title", "url": "https://example.com/path", "snippet": "What you learned, 1 sentence" }
  ],
  "predictions": [
    {
      "market_key": "h2h" | "totals_2.5" | "btts" | "spreads_-1" | "...",
      "pick": "<one of the outcome labels for this market>",
      "confidence": 0.0,
      "probabilities": { "<outcome>": 0.0, ... },
      "reasoning": "2-4 sentences citing the key factors.",
      "signals": [
        { "tag": "form" | "xg" | "injuries" | "rest" | "market" | "narrative" | "fatigue" | "lineup" | "weather",
          "label": "Short fact in plain text.",
          "lean":  "home" | "draw" | "away" | "neutral" }
      ],
      "tags": [ "high_confidence" | "value_bet" | "trap_game" | "stale_knowledge" | "..." ]
    }
  ]
}

User brief (JSON)

{
    "event": {
        "id": 13426,
        "sport": "basketball",
        "venue": "College Park Center",
        "league": "Women's National Basketball Association",
        "starts_at": "2026-07-19T17:00:00+00:00",
        "starts_at_human": "Sun, 19 Jul 2026 17:00:00 GMT"
    },
    "teams": {
        "away": "Los Angeles Sparks",
        "home": "Dallas Wings"
    },
    "version": "v2",
    "sport_focus": [
        "Pace is the master variable for totals — multiply both teams' possessions-per-game tendencies, not just their points.",
        "Check the injury/rest report first: a star sitting (or load-managed on a back-to-back) reshapes the spread and total.",
        "Weigh offensive vs defensive rating and three-point volume/variance — 3PT-heavy teams have wider outcome distributions.",
        "Bench depth and foul trouble swing close games; note rotation reliability.",
        "Back-to-backs and travel cause real fatigue — flag the schedule spot for each side.",
        "Home-court edge is meaningful but smaller than star availability."
    ],
    "team_context": {
        "note": "Reference data from our settled-results database. Verify + extend it with your own research; it is not a substitute for current team news.",
        "away_form": {
            "last": "W",
            "record": "1W-0D-0L",
            "scored": 88,
            "matches": 1,
            "conceded": 83
        },
        "home_form": {
            "last": "LW",
            "record": "1W-0D-1L",
            "scored": 168,
            "matches": 2,
            "conceded": 154
        },
        "rest_days": {
            "away": 38,
            "home": 35
        }
    },
    "market_consensus": {
        "h2h": [],
        "note": "No bookmaker consensus available at build time — predict from public knowledge.",
        "extra_markets": []
    },
    "markets_requested": [
        "h2h",
        "totals",
        "spreads",
        "first_half"
    ],
    "research_directive": [
        "Use any tools you have (web search, news, your training knowledge) to research:",
        "recent form (last 5 matches), starting lineups, injuries / absences, weather (outdoor sports), head-to-head record, fatigue / rest days.",
        "Cite specific sources in `sources_cited` when you use external tools.",
        "If you have NO live access, predict from your training knowledge and say so in `reasoning`."
    ]
}

The hash above is SHA-256 of the canonical JSON brief. Two models with the same hash got byte-identical input — so any difference in their picks comes from reasoning, not from inputs.

Research trail

What each AI looked up before picking

Unlock sources · Pro

Results settle automatically once the final score lands. Picks are permanent — no hindsight edits.

Recent recaps

How the AI lineup did on other recent matches.

Share
Share X Reddit WhatsApp Telegram Facebook

Get the AI consensus before kickoff

Free. Pre-match alert per AI + see your picks graded as results land.

Sign up free →