Model comparison
GPT-4 vs Mercury
Mercury is the stronger model overall, scoring 37.6 to 29.1 on the Noometry Index.
Last verified . 8 shared benchmarks.
Summary
- They share 8 benchmarks with published results for both. GPT-4 scores higher in 2 categories and Mercury in 4 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury leads 46.2 to 34.9.
Side by side
| GPT-4 | Mercury | |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 29.1 | 37.6 |
| Released | 2023-03-14 | — |
| Weights | Proprietary | Proprietary |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $30 | — |
| Output $ / M tokens | $60 | — |
| Results tracked | 38 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury leads
GPT-4: 31.6 (#283), Mercury: 38.7 (#170)
| Benchmark | GPT-4 | Mercury |
|---|---|---|
| LMArena Coding | 1254 | 1322 |
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| HumanEval+ | 79.3% | — |
Agentic & Tool Use Not comparable
GPT-4: —, Mercury: —
| Benchmark | GPT-4 | Mercury |
|---|---|---|
| METR Time Horizons | 36.1% | — |
Reasoning Too close to call
GPT-4: 17.8 (#289), Mercury: 17.5 (#293)
| Benchmark | GPT-4 | Mercury |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1285 |
| Kagi LLM Benchmark | — | 21.6% |
| Chess Puzzles | 4% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| Epoch Capabilities Index | 125.89 | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |
Math Not comparable
GPT-4: 10.8 (#309), Mercury: —
| Benchmark | GPT-4 | Mercury |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| LMArena Math | 1269 | — |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |
Knowledge Not comparable
GPT-4: 18.4 (#282), Mercury: —
| Benchmark | GPT-4 | Mercury |
|---|---|---|
| GPQA Diamond | 35.7% | — |
| LMArena Expert | 1211 | — |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |
Multilingual Mercury leads
GPT-4: 40.6 (#215), Mercury: 41.6 (#206)
| Benchmark | GPT-4 | Mercury |
|---|---|---|
| LMArena Non-English | 1246 | 1260 |
| LMArena Chinese | 1242 | — |
| LMArena French | 1283 | — |
| LMArena German | 1251 | — |
| LMArena Japanese | 1209 | — |
| LMArena Korean | 1184 | — |
| LMArena Russian | 1251 | — |
| LMArena Spanish | 1261 | — |
Instruction Following Too close to call
GPT-4: 65.3 (#222), Mercury: 65.2 (#224)
| Benchmark | GPT-4 | Mercury |
|---|---|---|
| LMArena Instruction Following | 1241 | 1239 |
Long Context Too close to call
GPT-4: 37.7 (#212), Mercury: 38.4 (#198)
| Benchmark | GPT-4 | Mercury |
|---|---|---|
| LMArena Longer Query | 1244 | 1266 |
Writing & Preference Mercury leads
GPT-4: 34.9 (#268), Mercury: 46.2 (#221)
| Benchmark | GPT-4 | Mercury |
|---|---|---|
| LMArena Text | 1263 | 1282 |
| LMArena Creative Writing | 1244 | 1191 |
| LMArena Multi-Turn | 1257 | 1282 |
| EQ-Bench Creative Writing | 752 | — |
Frequently asked questions
Is GPT-4 better than Mercury?
Mercury is the stronger model overall, scoring 37.6 to 29.1 on the Noometry Index.
Is GPT-4 or Mercury better for coding?
Mercury scores higher on coding benchmarks: 38.7 versus 31.6 in the Noometry coding category.
How many benchmarks do GPT-4 and Mercury share?
8 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Mercury has 9.