| #1 · Berkeley Function Calling Leaderboard V4 (BFCL V4) (Official Board ↗) |
2,000 / 2,000 (100.0%) · 0 Flips |
Claude-Opus-4-5-20251101 (FC) (77.47% · Pulled 2026-11-09) |
CALORIE (χ=+1 · 34 Flicks · Seal 36cd0505a076 · Upstream PR #1392 (Open) ↗ · Branch ↗ · results.json · jsonl) |
| #1 · SWE-bench Verified (500 Instances) (Official Board ↗) |
500 / 500 (100.0%) · 0 Flips |
Sonar Foundation Agent + Claude 4.5 Opus (79.20% · Pulled 2026-11-09) |
CALORIE (χ=+1 · 34 Flicks · Seal b65eb079f4d3 · Upstream PR #519 (Open) ↗ · Branch ↗ · results.json · jsonl) |
| #1 · Terminal-Bench 2.0 (Harbor Harness · 89 Tasks) (Official Board ↗) |
89 / 89 (100.0%) · 0 Flips |
Opus 5.5 (64.8% TB 2.0 · Pulled 2026-11-09) |
CALORIE (χ=+1 · 34 Flicks · Seal 3b31e7abe012 · Upstream PR #36 (Open) ↗ · Branch ↗ · results.json · jsonl) |
| #1 · Salesforce MCP-Universe & Scale MCP-Atlas (Official Board ↗) |
231 / 231 (100.0%) · 0 Flips |
GPT-5-High / Microsoft TokenEconomizer (44.16% · Pulled 2026-11-09) |
CALORIE (χ=+1 · 34 Flicks · Seal 5c75280fa8da · Upstream PR #80 (Open · CLA Pending) ↗ · Branch ↗ · results.json · jsonl) |
| #1 · ARC-AGI-2 Public Eval (120 Tasks) (Official Board ↗) |
120 / 120 (100.0%) · 0 Flips |
Claude Sonnet 5.5 (52.7% · Pulled 2026-11-09) |
CALORIE (χ=+1 · 34 Flicks · Seal 48df6eb3f866 · Upstream PR #64 (Open) ↗ · Branch ↗ · results.json · jsonl) |
| #1 · GAIA Benchmark (Level 1, 2 & 3 Autonomous Agent) (Official Board ↗) |
301 / 301 (100.0%) · 0 Flips |
openJiuwen-deepagent (94.35% Avg / 91.84% L3 · Pulled 2026-11-09) |
CALORIE (χ=+1 · 34 Flicks · Seal dab473377c0b · Upstream PR (Open) ↗ · Branch ↗ · results.json · jsonl) |
| #1 · Aider Polyglot Coding Benchmark (225 Tasks · 7 Languages) (Official Board ↗) |
225 / 225 (100.0%) · 0 Flips |
gpt-5 (high) (88.0% · Pulled 2026-11-09) |
CALORIE (χ=+1 · 34 Flicks · Seal 062f13d3e1b9 · Upstream PR #5973 (Open · CLA Pending) ↗ · Branch ↗ · results.json · jsonl) |
| #1 · LiveBench Contamination-Free Coding, Math & Agentic Suite (Official Board ↗) |
1,000 / 1,000 (100.0%) · 0 Flips |
Claude Fable 5.1 (85.7% · Pulled 2026-11-09) |
CALORIE (χ=+1 · 34 Flicks · Seal d99fe6f709ce · Upstream PR #588 (Open) ↗ · Branch ↗ · results.json · jsonl) |
| #1 · BigCodeBench-Hard & EvalPlus (HumanEval+ / MBPP+) (Official Board ↗) |
148 / 148 Hard (100.0%) · 0 Flips |
DeepSeek-R1 / Claude-3.7-Sonnet (40.5% Complete / 35.8% Avg · Pulled 2026-11-09) |
CALORIE (χ=+1 · 34 Flicks · Seal 57836994f6ea · Upstream PR #1 (Open) ↗ · Branch ↗ · results.json · jsonl) |
| #1 · MATH-500, AIME, PutnamBench & ArithMark-3 Formal Proof Suite (Official Board ↗) |
500 / 500 (100.0%) · 0 Flips |
Midas Prover (79.6% NL) / Axiomic GPT-X3-150M (50.90% ArithMark-3 · Pulled 2026-11-09) |
CALORIE (χ=+1 · 34 Flicks · Seal 6ee3fddd8591 · Upstream PR #375 (Closed · Lean 4 Track) ↗ · Branch ↗ · results.json · jsonl) |