Hugo GastonvsSho Shimabukuro
SSYour call
Who wins? One tap, no signup.
AI predictions
2 markets · 3 models
Ask the AIsWho picked what
32 models × 2 markets · click a row to see reasoning
| Model |
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
|
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
|
|
|---|---|---|---|
| Consensus |
Over 2.5 2/6 models |
Hugo Gaston 3/3 models |
|
Claude Opus 4.7 FlagshipAnthropic |
Flagship picks across 2 markets — unlock with Pro
Get Pro
|
||
|
Claude Opus 4.7 FlagshipAnthropic |
Flagship picks across 2 markets — unlock with Pro
Get Pro
|
||
|
Claude Opus 4.6 FlagshipAnthropic |
Flagship picks across 2 markets — unlock with Pro
Get Pro
|
||
|
Claude Opus 4.6 FlagshipAnthropic |
Flagship picks across 2 markets — unlock with Pro
Get Pro
|
||
|
Claude Opus 4.8 FlagshipAnthropic |
Flagship picks across 2 markets — unlock with Pro
Get Pro
|
||
|
Claude Opus 4.8 FlagshipAnthropic |
Flagship picks across 2 markets — unlock with Pro
Get Pro
|
||
|
Claude Sonnet 4.6 FlagshipAnthropic |
Flagship picks across 2 markets — unlock with Pro
Get Pro
|
||
|
Claude Sonnet 4.6 FlagshipAnthropic |
Flagship picks across 2 markets — unlock with Pro
Get Pro
|
||
|
Claude Haiku 4.5 Anthropic |
60%
Over 21.5 |
58%
Hugo Gaston |
|
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
60%
Over 21.5 If the match extends to 3 sets as predicted above, the total games will typically range 21–24 in a competitive ATP 250 match. A 6-4, 6-3, 6-...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
58%
Hugo Gaston Based on training knowledge through September 2025, Hugo Gaston has established a higher ATP ranking and more consistent performance at hard... |
|||
|
Claude Haiku 4.5 Anthropic |
60%
Over 21.5 |
58%
Hugo Gaston |
|
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
60%
Over 21.5 If the match extends to 3 sets as predicted above, the total games will typically range 21–24 in a competitive ATP 250 match. A 6-4, 6-3, 6-...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
58%
Hugo Gaston Based on training knowledge through September 2025, Hugo Gaston has established a higher ATP ranking and more consistent performance at hard... |
|||
GPT-5 FlagshipOpenai |
Flagship picks across 2 markets — unlock with Pro
Get Pro
|
||
|
GPT-5 FlagshipOpenai |
Flagship picks across 2 markets — unlock with Pro
Get Pro
|
||
|
GPT-5 Mini Openai |
— | — | |
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
No pick on this market.
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
No pick on this market. |
|||
|
GPT-5 Mini Openai |
— | — | |
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
No pick on this market.
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
No pick on this market. |
|||
|
GPT-4o Mini Openai |
— | — | |
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
No pick on this market.
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
No pick on this market. |
|||
|
GPT-4o Mini Openai |
— | — | |
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
No pick on this market.
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
No pick on this market. |
|||
|
o4-mini FlagshipOpenai |
Flagship picks across 2 markets — unlock with Pro
Get Pro
|
||
|
o4-mini FlagshipOpenai |
Flagship picks across 2 markets — unlock with Pro
Get Pro
|
||
Grok 4.3 FlagshipXai |
Flagship picks across 2 markets — unlock with Pro
Get Pro
|
||
|
Grok 4.3 FlagshipXai |
Flagship picks across 2 markets — unlock with Pro
Get Pro
|
||
|
Grok 4 Fast Xai |
62%
under 2.5 |
58%
Hugo Gaston |
|
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
62%
under 2.5 Both players' serve-heavy styles and limited head-to-head suggest a straight-sets outcome more often than not. Training data through 2023 sh...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
58%
Hugo Gaston Hugo Gaston holds a slight edge on hard courts based on training data through 2023, with better recent movement and return stats against sim... |
|||
|
Grok 4 Fast Xai |
62%
under 2.5 |
58%
Hugo Gaston |
|
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
62%
under 2.5 Both players' serve-heavy styles and limited head-to-head suggest a straight-sets outcome more often than not. Training data through 2023 sh...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
58%
Hugo Gaston Hugo Gaston holds a slight edge on hard courts based on training data through 2023, with better recent movement and return stats against sim... |
|||
Gemini 3.1 Pro Flagship |
Flagship picks across 2 markets — unlock with Pro
Get Pro
|
||
|
Gemini 3.1 Pro Flagship |
Flagship picks across 2 markets — unlock with Pro
Get Pro
|
||
|
Gemini 2.5 Pro Flagship |
Flagship picks across 2 markets — unlock with Pro
Get Pro
|
||
|
Gemini 2.5 Pro Flagship |
Flagship picks across 2 markets — unlock with Pro
Get Pro
|
||
|
Gemini 2.5 Flash |
— | — | |
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
No pick on this market.
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
No pick on this market. |
|||
|
Gemini 2.5 Flash |
— | — | |
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
No pick on this market.
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
No pick on this market. |
|||
|
Gemini 2.5 Flash-Lite |
— | — | |
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
No pick on this market.
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
No pick on this market. |
|||
|
Gemini 2.5 Flash-Lite |
— | — | |
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
No pick on this market.
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
No pick on this market. |
|||
DeepSeek V3 Deepseek |
54%
Over 2.5 |
66%
Hugo Gaston |
|
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
54%
Over 2.5 Shimabukuro is a durable returner who tends to keep sets close even when outgunned, and Hangzhou early-round conditions often reward grindin...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
66%
Hugo Gaston No live tools were available, so this is based on training data through 2025-09. Gaston is the higher-ceiling left-hander with substantially... |
|||
|
DeepSeek V3 Deepseek |
54%
Over 2.5 |
66%
Hugo Gaston |
|
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
54%
Over 2.5 Shimabukuro is a durable returner who tends to keep sets close even when outgunned, and Hangzhou early-round conditions often reward grindin...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
66%
Hugo Gaston No live tools were available, so this is based on training data through 2025-09. Gaston is the higher-ceiling left-hander with substantially... |
|||
Over / Under
ConsensusOver 2.5 2/6
Claude Haiku 4.5
60%
Over 21.5
If the match extends to 3 sets as predicted above, the total games will typically range 21–24 in a competitive ATP 250 match. A 6-4, 6-3, 6-...
Claude Haiku 4.5
60%
Over 21.5
If the match extends to 3 sets as predicted above, the total games will typically range 21–24 in a competitive ATP 250 match. A 6-4, 6-3, 6-...
GPT-5 Mini
—
GPT-5 Mini
—
GPT-4o Mini
—
GPT-4o Mini
—
Grok 4 Fast
62%
under 2.5
Both players' serve-heavy styles and limited head-to-head suggest a straight-sets outcome more often than not. Training data through 2023 sh...
Grok 4 Fast
62%
under 2.5
Both players' serve-heavy styles and limited head-to-head suggest a straight-sets outcome more often than not. Training data through 2023 sh...
Gemini 2.5 Flash
—
Gemini 2.5 Flash
—
Gemini 2.5 Flash-Lite
—
Gemini 2.5 Flash-Lite
—
DeepSeek V3
54%
Over 2.5
Shimabukuro is a durable returner who tends to keep sets close even when outgunned, and Hangzhou early-round conditions often reward grindin...
DeepSeek V3
54%
Over 2.5
Shimabukuro is a durable returner who tends to keep sets close even when outgunned, and Hangzhou early-round conditions often reward grindin...
Match winner
ConsensusHugo Gaston 3/3
Claude Haiku 4.5
58%
Hugo Gaston
Based on training knowledge through September 2025, Hugo Gaston has established a higher ATP ranking and more consistent performance at hard...
Claude Haiku 4.5
58%
Hugo Gaston
Based on training knowledge through September 2025, Hugo Gaston has established a higher ATP ranking and more consistent performance at hard...
GPT-5 Mini
—
GPT-5 Mini
—
GPT-4o Mini
—
GPT-4o Mini
—
Grok 4 Fast
58%
Hugo Gaston
Hugo Gaston holds a slight edge on hard courts based on training data through 2023, with better recent movement and return stats against sim...
Grok 4 Fast
58%
Hugo Gaston
Hugo Gaston holds a slight edge on hard courts based on training data through 2023, with better recent movement and return stats against sim...
Gemini 2.5 Flash
—
Gemini 2.5 Flash
—
Gemini 2.5 Flash-Lite
—
Gemini 2.5 Flash-Lite
—
DeepSeek V3
66%
Hugo Gaston
No live tools were available, so this is based on training data through 2025-09. Gaston is the higher-ceiling left-hander with substantially...
DeepSeek V3
66%
Hugo Gaston
No live tools were available, so this is based on training data through 2025-09. Gaston is the higher-ceiling left-hander with substantially...
Model confidence
Conviction in pick · Match winner
DeepSeek V3
Hugo Gaston
DeepSeek V3
Hugo Gaston
Claude Haiku 4.5
Hugo Gaston
Claude Haiku 4.5
Hugo Gaston
Grok 4 Fast
Hugo Gaston
Grok 4 Fast
Hugo Gaston
Model track records
LifetimeEvery graded pick across all sports — auto-settled the moment results land, wins and losses both counted. Ranked by win rate.
Units = net profit at flat 1-unit stakes. The full sortable board lives on the leaderboard.
Refresh the read
Team newsRe-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.
Verifiable brief
Identical prompt sent to every AI · SHA-256 verified
hash:
0ac374f2f8084db7…
- Kickoff
- Wed, Sep 23 · 04:00 GMT+0200
- Markets
- Match winner · Total sets · Total games
- 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 3. 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 3, in this order): h2h | totals_sets | totals_games
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": 47853,
"sport": "tennis",
"venue": null,
"league": "Hangzhou Open",
"starts_at": "2026-09-23T04:00:00+02:00",
"starts_at_human": "Wed, 23 Sep 2026 02:00:00 GMT"
},
"teams": {
"away": "Sho Shimabukuro",
"home": "Hugo Gaston"
},
"version": "v2",
"sport_focus": [
"Surface is paramount — weigh each player's record and movement on THIS surface (hard/clay/grass), not their overall ranking.",
"Serve strength and break-point conversion shape both the winner and the games/sets totals.",
"Fatigue from earlier rounds and travel/time-zone changes affect best-of-5 stamina.",
"Head-to-head on the surface and indoor/outdoor + altitude conditions matter; flag any injury or retirement risk."
],
"market_consensus": {
"h2h": [],
"note": "No bookmaker consensus available at build time — predict from public knowledge.",
"extra_markets": []
},
"markets_requested": [
"h2h",
"totals_sets",
"totals_games"
],
"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.
Results settle automatically once the final score lands. Picks are permanent — no hindsight edits.
Get the AI consensus before kickoff
Free. Pre-match alert per AI + see your picks graded as results land.