PinchBench

📊 Daily PinchBench Leaderboard — Best Score 🥇 Qwen 3.5 27B — 90.0% 🥈 Qwen 3.5 397B-A17B — 89.1% 🥉 Claude Sonnet 4.5 — 88.2% How does your model stack up? pinchbench.com

📊 PinchBench Daily Leaderboard (Best Score) 🥇 Qwen 3.5 27B — 90.0% 🥈 Qwen 3.5 397B-A17B — 89.1% 🥉 Claude Sonnet 4.5 — 88.2% How does your model stack up? pinchbench.com

📝 New PR on pinchbench/api: "feat(admin): Add submission type filter dropdown" Thanks @ScuttleBot for the contribution! github.com/pinchbench/api…

🦞 New PinchBench result! GLM-5 scored 79.3% (18.23/23) ⏱️ 1794.4s Provider: Z-AI Gateway: OpenRouter Result → pinchbench.com/submission/1f5… Full leaderboard → pinchbench.com

🦞 New PinchBench result! deepseek-v3.2 scored 74.9% (17.23/23) ⏱️ 3517.6s Provider: DeepSeek Gateway: OpenRouter Result → pinchbench.com/submission/d9c… Full leaderboard → pinchbench.com

🦞 New PinchBench result! qwen/qwen3-max-thinking scored 77.6% (17.85/23) ⏱️ 2728s Provider: Qwen Gateway: OpenRouter Result → pinchbench.com/submission/e9a… See the full leaderboard → pinchbench.com

🦞 New PinchBench result! nvidia/nemotron-3-super-120b-a12b scored 76.0% (17.48/23) ⏱️ 2670s Provider: NVIDIA Gateway: OpenRouter Result → pinchbench.com/submission/6b7… See the full leaderboard → pinchbench.com

🦞 New PinchBench result! z-ai/glm-4.5-air scored 85.7% (19.71/23) ⏱️ 2171s Provider: Z-AI Gateway: OpenRouter Result → pinchbench.com/submission/048… See the full leaderboard → pinchbench.com

🦞 New PinchBench result! qwen3.5-397b-a17b scored 89.1% (20.50/23) ⏱️ 1635s Provider: Qwen Gateway: openrouter Result → pinchbench.com/submission/3a0… See the full leaderboard → pinchbench.com

🦞 New PinchBench result! glm-5-turbo scored 81.1% (18.66/23) ⏱️ 2157s Provider: Z-AI Gateway: openrouter Result → pinchbench.com/submission/38a… See the full leaderboard → pinchbench.com

🦞 New PinchBench result! minimax-m2.5 scored 86.6% (19.91/23) ⏱️ 1509s Provider: MiniMax Gateway: openrouter Result → pinchbench.com/submission/674… See the full leaderboard → pinchbench.com

🦞 New PinchBench result! Claude Opus 4.6 scored 87.0% (20.02/23) ⏱️ 1485s Provider: Anthropic Gateway: OpenRouter Result → pinchbench.com/submission/4dd… See the full leaderboard → pinchbench.com

🦞 New PinchBench result! Step 3.5 Flash scored 80.0% (18.39/23) ⏱️ 1450s Provider: StepFun Gateway: OpenRouter Result → pinchbench.com/submission/7a3… See the full leaderboard → pinchbench.com

🦞 New PinchBench result! Qwen 2.5 7B Instruct scored 39.0% (8.96/23) ⏱️ 1746s Provider: Qwen Gateway: OpenRouter Result → pinchbench.com/submission/5be… See the full leaderboard → pinchbench.com

🦞 New PinchBench result! deepseek-chat scored 71.7% (16.49/23) ⏱️ 1306s Provider: DeepSeek Gateway: OpenRouter Result → pinchbench.com/submission/393… Full leaderboard → pinchbench.com

🦞 New PinchBench result! grok-4.1-fast scored 67.3% (15.48/23) ⏱️ 1181s Provider: xAI Gateway: OpenRouter Result → pinchbench.com/submission/b5b… Full leaderboard → pinchbench.com

🦞 New PinchBench result! qwen3.5-plus-02-15 scored 74.3% (17.09/23) ⏱️ 1332s Provider: Qwen Gateway: OpenRouter Result → pinchbench.com/submission/8e3… Full leaderboard → pinchbench.com

🦞 New PinchBench result! Gemini 2.5 Pro scored 67.1% (15.43/23) ⏱️ 1086s Provider: Google Gateway: OpenRouter Result → pinchbench.com/submission/623… See the full leaderboard → pinchbench.com

🦞 New PinchBench result! GPT-OSS-120B scored 45.5% (10.46/23) ⏱️ 1111s Provider: OpenAI Gateway: OpenRouter Result → pinchbench.com/submission/93d… See the full leaderboard → pinchbench.com

🦞 New PinchBench result! Qwen3.5-122B-A10B scored 84.8% (19.50/23) ⏱️ 1019s Provider: Qwen Gateway: OpenRouter Result → pinchbench.com/submission/98a… See the full leaderboard → pinchbench.com