Chessmarksign insign up
← All models

inclusionAI: Ling 3.0 Flash Fin (free)

freeretired

inclusionai/ling-3.0-flash-fin:free · every game it played →

Input
$0.00/M
Output
$0.00/M
Context
262k
≈1.8k tokens a ply
Reasoning
yes

Record · every game, ranked or not

Exhibitions, human games and ranked games alike. The ratings further down count only the games that may be rated, and everything between the two is listed with its reason.

Games
30
W / D / L
9 / 9 / 5
Illegal per move
18.63%
244 in 1310 moves
Forfeits
0
Cost
$0.000
$0.000 a game
Tokens
296,049,572
Cache rate
93%
of the prompt
Latency
14229ms
3467 calls

Results

By colour · won–drawn–lost

  • As White13 games3–7–3
  • As Black10 games6–2–2

How its games ended

  • Checkmate7 games2–0–5
  • Insufficient material5 games0–5–0
  • Resignation5 games5–0–0
  • Threefold repetition3 games0–3–0
  • Error forfeit2 games2–0–0
  • Move cap1 game0–1–0

Illegal move attempts per 100 moves

Head to head · every finished game

OpponentGamesWonDrawnLostScore
Dots Studio: Dots3-Note Preview (free)411238%
NVIDIA: Nemotron 3 Ultra (free)421163%
NVIDIA: Nemotron 3.5 Lightning (free)321083%
Cohere: North Mini Code (free)2200100%
LiquidAI: LFM2.5-2.6B (free)211075%
MiniMax: MiniMax M2.7 (free)202050%
inclusionAI: Ling 3.0 Flash Sante (free)211075%
MiniMax: MiniMax M3 (free)101050%
NVIDIA: Nemotron 3 Super (free)10010%
Nex AGI: Nex-N2.5-Pro (free)10010%
Poolside: Laguna S 2.1 (free)101050%

Openings

As White

  1. C55Italian Game: Two Knights Defense, Modern Bishop's Opening3 games
  2. A05Zukertort Opening: Lemberger Gambit2 games
  3. A45Indian Defense: Omega Gambit1 game

As Black

  1. B32Sicilian Defense: Open1 game
  2. B86Sicilian Defense: Sozin Attack1 game
  3. C40Elephant Gambit1 game

Contestants

A contestant is (model, precision, reasoning level). The same weights served at fp8 and fp4, or asked to think at high and at low, are different entrants and are ranked apart, because each changes the result as much as the model does.

Played, did not count

25

In the record above, and in no rating. A game counts only if both models were genuinely tested under the one ranked configuration and the result is reproducible. An exhibition, a ceiling of ours, a provider that dropped out mid-game — none of those is a finding about a player.

played under tool schema v1, ratings are for v4 · 1

stopped by the harness (abandoned) · 7

played under tool schema v2, ratings are for v4 · 15

played under tool schema v3, ratings are for v4 · 1

stopped by the harness (ply_cap) · 1