Model comparison
Claude 2.1 vs Claude Sonnet 4.6
Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 25.2 on the Noometry Index.
Last verified . 6 shared benchmarks.
Summary
- They share 6 benchmarks with published results for both. Claude 2.1 scores higher in 0 categories and Claude Sonnet 4.6 in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4.6 leads 52.9 to 10.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.9% for Claude 2.1 and 85.8% for Claude Sonnet 4.6.
Side by side
| Claude 2.1 | Claude Sonnet 4.6 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 25.2 | 50.3 |
| Released | 2023-11-21 | 2026-02-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 128K |
| Input $ / M tokens | — | $3 |
| Output $ / M tokens | — | $15 |
| Results tracked | 7 | 57 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.6 leads
Claude 2.1: 26.2 (#327), Claude Sonnet 4.6: 46.3 (#67)
| Benchmark | Claude 2.1 | Claude Sonnet 4.6 |
|---|---|---|
| WeirdML | 7.1% | 66.1% |
| SWE-bench Verified | — | 75.2% |
| DeepSWE | — | 29.9% |
| FrontierCode | — | 24.3% |
| LMArena WebDev | — | 1522 |
| SciCode | — | 46.8% |
| LMArena Coding | — | 1504 |
| ALE-Bench | — | 1,327 |
Agentic & Tool Use Not comparable
Claude 2.1: —, Claude Sonnet 4.6: 39.1 (#28)
| Benchmark | Claude 2.1 | Claude Sonnet 4.6 |
|---|---|---|
| Terminal-Bench | — | 53.4% |
| APEX-Agents | — | 43% |
| OSWorld 2.0 | — | 9.3% |
| DeepResearch Bench | — | 54.9% |
| OSWorld | — | 72.1% |
| ExploitBench | — | 23.6% |
| GBAEval | — | 48.8% |
| GDP.pdf | — | 18% |
| LMArena Search | — | 1221 |
| Vending-Bench 2 | — | 7,204 |
Reasoning Claude Sonnet 4.6 leads
Claude 2.1: 21.4 (#221), Claude Sonnet 4.6: 46.1 (#45)
| Benchmark | Claude 2.1 | Claude Sonnet 4.6 |
|---|---|---|
| DTBench | 51% | 89.9% |
| Epoch Capabilities Index | 119.27 | 152.24 |
| ForecastBench | 54.2 | 62 |
| ARC-AGI-2 | — | 60.4% |
| NYT Connections (extended) | — | 80.9% |
| ARC-AGI-1 | — | 86.5% |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 76.3% |
| LMArena Hard Prompts | — | 1484 |
| Mystery Game Puzzles | — | 16% |
| LMCA | — | 46.5% |
Math Claude Sonnet 4.6 leads
Claude 2.1: 10.2 (#315), Claude Sonnet 4.6: 52.9 (#49)
| Benchmark | Claude 2.1 | Claude Sonnet 4.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | 85.8% |
| ProofBench | — | 45% |
| LMArena Math | — | 1462 |
| FrontierMath (Feb 2025 set) | — | 32.4% |
| FrontierMath Tier 4 (v1) | — | 8.3% |
Knowledge Claude Sonnet 4.6 leads
Claude 2.1: 15.4 (#292), Claude Sonnet 4.6: 51.7 (#65)
| Benchmark | Claude 2.1 | Claude Sonnet 4.6 |
|---|---|---|
| GPQA Diamond | 33% | 87.4% |
| SimpleQA Verified | — | 35.5% |
| Vectara Hallucination Rate | — | 10.6% |
| LMArena Expert | — | 1500 |
| MMLU | 73.5% | — |
Multimodal Not comparable
Claude 2.1: —, Claude Sonnet 4.6: 38.0 (#68)
| Benchmark | Claude 2.1 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Vision | — | 1283 |
| Blueprint-Bench 2 | — | 6.7% |
| LMArena Document | — | 1482 |
Multilingual Not comparable
Claude 2.1: —, Claude Sonnet 4.6: 54.4 (#41)
| Benchmark | Claude 2.1 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Non-English | — | 1440 |
| LMArena Chinese | — | 1491 |
| LMArena French | — | 1465 |
| LMArena German | — | 1428 |
| LMArena Japanese | — | 1420 |
| LMArena Korean | — | 1411 |
| LMArena Russian | — | 1440 |
| LMArena Spanish | — | 1464 |
Instruction Following Not comparable
Claude 2.1: —, Claude Sonnet 4.6: 77.4 (#25)
| Benchmark | Claude 2.1 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Instruction Following | — | 1475 |
Long Context Not comparable
Claude 2.1: —, Claude Sonnet 4.6: 45.3 (#44)
| Benchmark | Claude 2.1 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Longer Query | — | 1479 |
Writing & Preference Not comparable
Claude 2.1: —, Claude Sonnet 4.6: 70.2 (#22)
| Benchmark | Claude 2.1 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Text | — | 1458 |
| LMArena Creative Writing | — | 1435 |
| EQ-Bench Creative Writing | — | 1810 |
| EQ-Bench 4 | — | 1207 |
| LMArena Multi-Turn | — | 1464 |
Frequently asked questions
Is Claude 2.1 better than Claude Sonnet 4.6?
Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 25.2 on the Noometry Index.
Is Claude 2.1 or Claude Sonnet 4.6 better for coding?
Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 26.2 in the Noometry coding category.
How many benchmarks do Claude 2.1 and Claude Sonnet 4.6 share?
6 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and Claude Sonnet 4.6 has 57.