Model comparison
Claude Sonnet 4.5 vs ERNIE 5.0 0110
Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 41.2 on the Noometry Index.
Last verified . 18 shared benchmarks.
BaiduSummary
- They share 18 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 6 categories and ERNIE 5.0 0110 in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Sonnet 4.5 leads 26.9 to 16.3.
- The biggest single-benchmark swing is NYT Connections (extended): 37.3% for Claude Sonnet 4.5 and 10.3% for ERNIE 5.0 0110.
Side by side
| Claude Sonnet 4.5 | ERNIE 5.0 0110 | |
|---|---|---|
| Provider | Anthropic | Baidu |
| Noometry Index | 44.0 | 41.2 |
| Released | 2025-09-29 | — |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 64K | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 73 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 47.8 (#54), ERNIE 5.0 0110: 42.3 (#94)
| Benchmark | Claude Sonnet 4.5 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Coding | 1489 | 1455 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Verified (bash only) | 71.4% | — |
| LMArena WebDev | 1393 | — |
| SWE-bench Multilingual | 67% | — |
| SciCode | 44.7% | — |
| GSO | 14.7% | — |
| WeirdML | 47.7% | — |
| ALE-Bench | 796.15 | — |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4.5: 38.1 (#30), ERNIE 5.0 0110: —
| Benchmark | Claude Sonnet 4.5 | ERNIE 5.0 0110 |
|---|---|---|
| Terminal-Bench | 46.5% | — |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |
Reasoning Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 26.9 (#113), ERNIE 5.0 0110: 16.3 (#296)
| Benchmark | Claude Sonnet 4.5 | ERNIE 5.0 0110 |
|---|---|---|
| NYT Connections (extended) | 37.3% | 10.3% |
| LMArena Hard Prompts | 1462 | 1446 |
| ARC-AGI-2 | 13.6% | — |
| SimpleBench | 54.3% | — |
| Kagi LLM Benchmark | 57.9% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 6% | — |
| Thematic Generalization | — | 41.7% |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 17% | — |
| DTBench | 83.2% | — |
| LMCA | 38.8% | — |
| Epoch Capabilities Index | 146.84 | — |
| ForecastBench | 61.9 | — |
Math ERNIE 5.0 0110 leads
Claude Sonnet 4.5: 31.9 (#190), ERNIE 5.0 0110: 36.5 (#111)
| Benchmark | Claude Sonnet 4.5 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Math | 1448 | 1437 |
| FrontierMath (Tiers 1-3) | 23.9% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| ProofBench | 19% | — |
| Omni-MATH | 55.3% | — |
| MATH Level 5 | 97.7% | — |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 48.4 (#70), ERNIE 5.0 0110: 39.2 (#125)
| Benchmark | Claude Sonnet 4.5 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Expert | 1483 | 1427 |
| GPQA Diamond | 82.3% | — |
| Humanity's Last Exam | 13.7% | — |
| SimpleQA Verified | 30.7% | — |
| MMLU-Pro | 86.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 68.6% | — |
Multimodal ERNIE 5.0 0110 leads
Claude Sonnet 4.5: 34.1 (#84), ERNIE 5.0 0110: 39.1 (#49)
| Benchmark | Claude Sonnet 4.5 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Vision | — | 1248 |
| VPCT | 39.8% | — |
| LMArena Document | 1450 | — |
Multilingual Too close to call
Claude Sonnet 4.5: 53.6 (#65), ERNIE 5.0 0110: 54.3 (#47)
| Benchmark | Claude Sonnet 4.5 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Non-English | 1425 | 1436 |
| LMArena Chinese | 1459 | 1512 |
| LMArena French | 1459 | 1466 |
| LMArena German | 1427 | 1462 |
| LMArena Japanese | 1390 | 1383 |
| LMArena Korean | 1403 | 1406 |
| LMArena Russian | 1436 | 1446 |
| LMArena Spanish | 1457 | 1473 |
Instruction Following Too close to call
Claude Sonnet 4.5: 75.2 (#74), ERNIE 5.0 0110: 74.7 (#88)
| Benchmark | Claude Sonnet 4.5 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Instruction Following | 1459 | 1413 |
| IFEval | 85% | — |
Long Context Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 45.2 (#45), ERNIE 5.0 0110: 43.4 (#90)
| Benchmark | Claude Sonnet 4.5 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Longer Query | 1476 | 1422 |
Writing & Preference Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 66.7 (#33), ERNIE 5.0 0110: 63.4 (#64)
| Benchmark | Claude Sonnet 4.5 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Text | 1439 | 1445 |
| LMArena Creative Writing | 1442 | 1426 |
| LMArena Multi-Turn | 1465 | 1433 |
| EQ-Bench Creative Writing | 1678 | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is Claude Sonnet 4.5 better than ERNIE 5.0 0110?
Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 41.2 on the Noometry Index.
Is Claude Sonnet 4.5 or ERNIE 5.0 0110 better for coding?
Claude Sonnet 4.5 scores higher on coding benchmarks: 47.8 versus 42.3 in the Noometry coding category.
How many benchmarks do Claude Sonnet 4.5 and ERNIE 5.0 0110 share?
18 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and ERNIE 5.0 0110 has 20.