Dashboards
Socratic Score = mean of normalized benchmarks. LM Arena: (ELO - 1000) / 400 × 100. Vending-Bench: balance / $10k × 100. SWE-bench, ARC-AGI, and HLE are used as-is (0-100%).
AI Socratic Leaderboard
Scores across benchmarks
| # | Model | Score | LM Arena ↗ | SWE-bench ↗ | ARC-AGI-2 ↗ | HLE ↗ | Vending ↗ | Prediction ↗ | Vibe Bench |
|---|---|---|---|---|---|---|---|---|---|
| 🥇 |  Gemini 3.1 Pro | 86.3 | - | - | - | - | - | +72.7% | - |
| 🥈 |  Claude Sonnet 4.6 | 72.0 | - | - | - | - | $7,204.14 | - | - |
| 🥉 |  DeepSeek V3 | 70.0 | - | 70.0% | - | - | - | - | - |
| 4 |  GLM 5 | 68.7 | - | 72.8% | - | - | $5,634.41 | +53.8% | - |
| 5 | Claude Opus 4.6 | 64.2 | - | 75.6% | - | - | $8,017.59 | -26.5% | - |
| 6 | Claude Opus 4.5 | 56.7 | - | 76.8% | - | - | - | -26.6% | - |
Vibe Bench
Community favorites · Socratic Feb · 0 responses
 Claude | 0 |
 ChatGPT | 0 |
 Gemini | 0 |
 Grok | 0 |
Open Source | 0 |
| Claude Code | 0 |
 Cursor | 0 |
| Codex | 0 |
 Perplexity | 0 |
 Windsurf | 0 |
Other Tools | 0 |
Vibe Bench: trends
Mentions per event (absolute count)
SWE-bench Bash ↗Verified
Real-world software engineering tasks
| # | Model | % Resolved |
|---|---|---|
| 🥇 | Claude 4.5 Opus (high reasoning) | 76.8% |
| 🥈 | Gemini 3 Flash (high reasoning) | 75.8% |
| 🥉 |  MiniMax M2.5 (high reasoning) | 75.8% |
| 4 | Claude Opus 4.6 | 75.6% |
| 5 | GPT-5-2 Codex | 72.8% |
| 6 |  GLM-5 (high reasoning) | 72.8% |
| 7 | GPT-5-2 (high reasoning) | 72.8% |
| 8 | GPT 5.2 Codex | 72.8% |
| 9 | Claude 4.5 Sonnet (high reasoning) | 71.4% |
| 10 | Kimi K2.5 (high reasoning) | 70.8% |
ARC-AGI-2 ↗Semi-Private
Abstract reasoning capabilities
| # | Model | Score |
|---|
Expert-level reasoning across disciplines
| # | Model | Accuracy |
|---|---|---|
| 🥇 | Gemini 3 Pro | 38.3% |
| 🥈 | GPT-5 | 25.3% |
| 🥉 | Grok 4 | 24.5% |
| 4 | Gemini 2.5 Pro | 21.6% |
| 5 | GPT-5-mini | 19.4% |
| 6 | Claude 4.5 Sonnet | 13.7% |
| 7 | Gemini 2.5 Flash | 12.1% |
| 8 |  DeepSeek-R1* | 8.5% |
| 9 | o1 | 8.0% |
| 10 | GPT-4o | 2.7% |
Vending-Bench 2 ↗Andon Labs
Long-term agentic coherence
| # | Model | Balance |
|---|---|---|
| 🥇 |  Claude Opus 4.7 | $10,936.76 |
| 🥈 |  Claude Opus 4.6 | $8,017.59 |
| 🥉 |  GPT-5.5 New | $7,523.84 |
| 4 |  Claude Sonnet 4.6 | $7,204.14 |
| 5 |  Kimi K2.6 New | $6,204.57 |
| 6 |  GPT-5.4 | $6,144.18 |
| 7 |  GPT-5.3-Codex | $5,940.12 |
| 8 |  GLM-5.1 | $5,634.41 |
| 9 |  Gemini 3 Pro | $5,478.16 |
| 10 |  Gemini 3.5 Flash | $5,396.42 |
Prediction Arena ↗Arcada Labs
AI prediction market performance
| # | Agent | Return | Sharpe |
|---|---|---|---|
| 🥇 | Gemini 3.1 Pro | 72.7% | 0.03 |
| 🥈 | GLM 5 | 53.8% | 0.03 |
| 🥉 | GPT 5.4 | 1.2% | 0.02 |
| 4 | GLM 4.7 | -15.4% | -0.12 |
| 5 | Mystery Model Alpha | -20.0% | -0.05 |
| 6 | Claude Opus 4.6 | -26.5% | -0.01 |
| 7 | Claude Opus 4.5 | -26.6% | -0.10 |
| 8 | GPT 5.2 | -26.8% | -0.09 |
| 9 | Grok 4.1 | -30.8% | -0.07 |
| 10 | Gemini 3 Pro | -31.0% | -0.11 |