Model comparison
Claude 2.1 vs Claude 3 Opus
Claude 3 Opus is the stronger model overall, scoring 29.5 to 25.2 on the Noometry Index.
Last verified . 7 shared benchmarks.
Summary
- They share 7 benchmarks with published results for both. Claude 2.1 scores higher in 1 category and Claude 3 Opus in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude 3 Opus leads 24.5 to 15.4.
- The biggest single-benchmark swing is GPQA Diamond: 33% for Claude 2.1 and 47.2% for Claude 3 Opus.
Side by side
| Claude 2.1 | Claude 3 Opus | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 25.2 | 29.5 |
| Released | 2023-11-21 | 2024-02-29 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3 Opus leads
Claude 2.1: 26.2 (#327), Claude 3 Opus: 32.9 (#267)
| Benchmark | Claude 2.1 | Claude 3 Opus |
|---|---|---|
| WeirdML | 7.1% | 19.2% |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 38.6% |
| LMArena Coding | — | 1264 |
| BigCodeBench Complete | — | 57.4% |
| HumanEval+ | — | 77.4% |
| MBPP+ | — | 73.3% |
Agentic & Tool Use Not comparable
Claude 2.1: —, Claude 3 Opus: 24.6 (#116)
| Benchmark | Claude 2.1 | Claude 3 Opus |
|---|---|---|
| Cybench | — | 10% |
| METR Time Horizons | — | 29.5% |
Reasoning Claude 2.1 leads
Claude 2.1: 21.4 (#221), Claude 3 Opus: 14.6 (#324)
| Benchmark | Claude 2.1 | Claude 3 Opus |
|---|---|---|
| DTBench | 51% | 61.6% |
| Epoch Capabilities Index | 119.27 | 126.91 |
| ForecastBench | 54.2 | 58.4 |
| SimpleBench | — | 23.5% |
| Chess Puzzles | — | 5% |
| EnigmaEval | — | 0.8% |
| LiveBench Reasoning | — | 40.6% |
| LMArena Hard Prompts | — | 1245 |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | — | 17% |
| LiveBench | — | 49.2% |
| WinoGrande | — | 88.5% |
Math Claude 3 Opus leads
Claude 2.1: 10.2 (#315), Claude 3 Opus: 14.8 (#299)
| Benchmark | Claude 2.1 | Claude 3 Opus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | 4.7% |
| LiveBench Math | — | 43.6% |
| LMArena Math | — | 1273 |
| MATH Level 5 | — | 37.5% |
Knowledge Claude 3 Opus leads
Claude 2.1: 15.4 (#292), Claude 3 Opus: 24.5 (#267)
| Benchmark | Claude 2.1 | Claude 3 Opus |
|---|---|---|
| GPQA Diamond | 33% | 47.2% |
| MMLU | 73.5% | 84.6% |
| SimpleQA Verified | — | 12.6% |
| Confabulations | — | 22.7% |
| LMArena Expert | — | 1223 |
Multimodal Not comparable
Claude 2.1: —, Claude 3 Opus: 27.1 (#116)
| Benchmark | Claude 2.1 | Claude 3 Opus |
|---|---|---|
| LMArena Vision | — | 1023 |
Multilingual Not comparable
Claude 2.1: —, Claude 3 Opus: 41.4 (#207)
| Benchmark | Claude 2.1 | Claude 3 Opus |
|---|---|---|
| LMArena Non-English | — | 1258 |
| LMArena Chinese | — | 1248 |
| LMArena French | — | 1275 |
| LMArena German | — | 1258 |
| LMArena Japanese | — | 1204 |
| LMArena Korean | — | 1187 |
| LMArena Russian | — | 1280 |
| LMArena Spanish | — | 1246 |
Instruction Following Not comparable
Claude 2.1: —, Claude 3 Opus: 64.1 (#228)
| Benchmark | Claude 2.1 | Claude 3 Opus |
|---|---|---|
| LiveBench Instruction Following | — | 63.9% |
| LMArena Instruction Following | — | 1248 |
Long Context Not comparable
Claude 2.1: —, Claude 3 Opus: 38.2 (#202)
| Benchmark | Claude 2.1 | Claude 3 Opus |
|---|---|---|
| LMArena Longer Query | — | 1259 |
Writing & Preference Not comparable
Claude 2.1: —, Claude 3 Opus: 47.2 (#213)
| Benchmark | Claude 2.1 | Claude 3 Opus |
|---|---|---|
| LMArena Text | — | 1262 |
| LMArena Creative Writing | — | 1235 |
| LMArena Multi-Turn | — | 1275 |
| LiveBench Language | — | 50.4% |
Frequently asked questions
Is Claude 2.1 better than Claude 3 Opus?
Claude 3 Opus is the stronger model overall, scoring 29.5 to 25.2 on the Noometry Index.
Is Claude 2.1 or Claude 3 Opus better for coding?
Claude 3 Opus scores higher on coding benchmarks: 32.9 versus 26.2 in the Noometry coding category.
How many benchmarks do Claude 2.1 and Claude 3 Opus share?
7 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and Claude 3 Opus has 46.