| Capability | Indexes | 891 | 169.9 |
| MMLU Pro | General QA | 496 | 93.4 |
| Humanity's Last Exam (Text-Only) | General QA | 488 | 63.1 |
| Artificial Analysis Progress Index v1 | Indexes | 484 | 351 |
| GPQA Diamond (Artificial Analysis avg@5) | General QA | 456 | 96.3 |
| SciCode (Artificial Analysis avg@3) | Science | 411 | 60.2 |
| AA-LCR v1.1 | Search | 406 | 88.7 |
| GPQA Diamond | General QA | 406 | 96.4 |
| CritPt (avg@5) | Science | 402 | 32.9 |
| AA-Omniscience Index | Indexes | 391 | 46.4 |
| Artificial Analysis Omniscience Accuracy | General QA | 391 | 66.2 |
| Artificial Analysis Omniscience Hallucination Rate | Safety | 391 | 0.9 |
| AA-LCR | Search | 357 | 78.2 |
| τ²-bench (Telecom) | Agents | 334 | 99.3 |
| IFBench (Artificial Analysis avg@5) | Chat & Writing | 333 | 83.4 |
| Terminal-Bench Hard | Code | 312 | 65.9 |
| MMLU | General QA | 296 | 93.4 |
| BuseyBench SVG | Multimodal | 282 | 8.0 |
| LiveCodeBench (Artificial Analysis) | Code | 277 | 91.7 |
| SnakeBench Average Apples | Games | 275 | 19.8 |
| SnakeBench Best Apples | Games | 275 | 34.0 |
| SnakeBench Rating | Games | 275 | 38.2 |
| SnakeBench Total Apples | Games | 275 | 1316 |
| SnakeBench Win Rate | Games | 275 | 100.0 |
| Artificial Analysis Openness Index | Indexes | 266 | 88.9 |
| HumanEval | Code | 258 | 99.3 |
| Arena Text — English (No Style Control) | Chat & Writing | 253 | 1530 |
| Arena Text — Exclude Ties (No Style Control) | Chat & Writing | 253 | 1569 |
| Arena Text — Exclude Ties (Style Controlled) | Chat & Writing | 253 | 1554 |
| Arena Text — Hard Prompts (No Style Control) | Chat & Writing | 253 | 1553 |
| Arena Text — Hard Prompts English (No Style Control) | Chat & Writing | 253 | 1545 |
| Arena Text — Instruction Following (No Style Control) | Chat & Writing | 253 | 1539 |
| Arena Text — Non-English (No Style Control) | Chat & Writing | 253 | 1537 |
| Arena Text — Non-English (Style Controlled) | Chat & Writing | 253 | 1521 |
| Arena Text — Software & IT Services (No Style Control) | Professional Work | 253 | 1555 |
| Arena Text — Writing, Literature & Language (No Style Control) | Professional Work | 253 | 1543 |
| LMArena Text Arena Elo | Chat & Writing | 253 | 1528 |
| LMArena Text Arena English Elo | Chat & Writing | 253 | 1523 |
| LMArena Text Arena Hard Prompts Elo | Chat & Writing | 253 | 1548 |
| LMArena Text Arena Hard Prompts English Elo | Chat & Writing | 253 | 1544 |
| LMArena Text Arena Industry: Writing, Literature & Language Elo | Chat & Writing | 253 | 1529 |
| LMArena Text Arena Instruction Following Elo | Chat & Writing | 253 | 1525 |
| LMArena Text Arena Occupational Software & IT Services Elo | Professional Work | 253 | 1552 |
| LMArena Text Overall No Style Control Elo | Chat & Writing | 253 | 1540 |
| Arena Text — Creative Writing (No Style Control) | Chat & Writing | 252 | 1534 |
| Arena Text — Entertainment, Sports & Media (No Style Control) | Professional Work | 252 | 1526 |
| Arena Text — Life, Physical & Social Science (No Style Control) | Professional Work | 252 | 1546 |
| Arena Text — Multi-turn (No Style Control) | Chat & Writing | 252 | 1565 |
| LMArena Text Arena Coding Elo | Code | 252 | 1573 |
| LMArena Text Arena Creative Writing Elo | Chat & Writing | 252 | 1520 |