Model comparison
GPT-4o mini vs Grok-2 (Dec 2024)
Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 25.5 on the Noometry Index.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. GPT-4o mini scores higher in 1 category and Grok-2 (Dec 2024) in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok-2 (Dec 2024) leads 29.8 to 17.7.
- The biggest single-benchmark swing is LiveBench Reasoning: 32.8% for GPT-4o mini and 54.8% for Grok-2 (Dec 2024).
Side by side
| GPT-4o mini | Grok-2 (Dec 2024) | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 25.5 | 33.7 |
| Released | 2024-07-18 | 2024-08-13 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 60 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-2 (Dec 2024) leads
GPT-4o mini: 22.0 (#335), Grok-2 (Dec 2024): 33.3 (#258)
| Benchmark | GPT-4o mini | Grok-2 (Dec 2024) |
|---|---|---|
| WeirdML | 11.8% | 22.2% |
| LiveBench Coding | 43.1% | 46.4% |
| LMArena Coding | 1290 | 1287 |
| Aider Polyglot | 3.6% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use Not comparable
GPT-4o mini: 27.5 (#101), Grok-2 (Dec 2024): —
| Benchmark | GPT-4o mini | Grok-2 (Dec 2024) |
|---|---|---|
| BALROG | 17.4% | — |
Reasoning Grok-2 (Dec 2024) leads
GPT-4o mini: 8.7 (#347), Grok-2 (Dec 2024): 16.9 (#299)
| Benchmark | GPT-4o mini | Grok-2 (Dec 2024) |
|---|---|---|
| SimpleBench | 10.7% | 22.7% |
| LiveBench Reasoning | 32.8% | 54.8% |
| LMArena Hard Prompts | 1267 | 1272 |
| DTBench | 54.4% | 65.2% |
| LiveBench Data Analysis | 50% | 54.5% |
| Epoch Capabilities Index | 126.56 | 130.48 |
| LiveBench | 41.3% | 54.3% |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 28.8% | — |
| Chess Puzzles | 0% | — |
| Mystery Game Puzzles | 12% | — |
| LMCA | 10.4% | — |
| PIQA | 88.7% | — |
Math Grok-2 (Dec 2024) leads
GPT-4o mini: 10.4 (#314), Grok-2 (Dec 2024): 20.8 (#284)
| Benchmark | GPT-4o mini | Grok-2 (Dec 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.9% | 11.5% |
| LiveBench Math | 36.3% | 54.9% |
| LMArena Math | 1267 | 1283 |
| MATH Level 5 | 52.6% | 63.5% |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| Omni-MATH | 28% | — |
| FrontierMath (Feb 2025 set) | — | 0.7% |
| GSM8K | 91.3% | — |
Knowledge Grok-2 (Dec 2024) leads
GPT-4o mini: 17.7 (#284), Grok-2 (Dec 2024): 29.8 (#233)
| Benchmark | GPT-4o mini | Grok-2 (Dec 2024) |
|---|---|---|
| GPQA Diamond | 37.7% | 53.8% |
| Confabulations | 37.2% | 20.1% |
| LMArena Expert | 1235 | 1254 |
| SimpleQA Verified | 8.3% | — |
| MMLU-Pro | 60.3% | — |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |
Multimodal Not comparable
GPT-4o mini: 25.9 (#122), Grok-2 (Dec 2024): —
| Benchmark | GPT-4o mini | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
Multilingual Grok-2 (Dec 2024) leads
GPT-4o mini: 42.0 (#199), Grok-2 (Dec 2024): 43.1 (#188)
| Benchmark | GPT-4o mini | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1266 | 1282 |
| LMArena Chinese | 1265 | 1289 |
| LMArena French | 1297 | 1318 |
| LMArena German | 1272 | 1287 |
| LMArena Japanese | 1216 | 1244 |
| LMArena Korean | 1195 | 1237 |
| LMArena Russian | 1275 | 1286 |
| LMArena Spanish | 1276 | 1281 |
Instruction Following Grok-2 (Dec 2024) leads
GPT-4o mini: 61.9 (#239), Grok-2 (Dec 2024): 66.9 (#202)
| Benchmark | GPT-4o mini | Grok-2 (Dec 2024) |
|---|---|---|
| LiveBench Instruction Following | 56.8% | 69.6% |
| LMArena Instruction Following | 1258 | 1270 |
| IFEval | 78.2% | — |
Long Context Too close to call
GPT-4o mini: 39.1 (#186), Grok-2 (Dec 2024): 38.8 (#190)
| Benchmark | GPT-4o mini | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1289 | 1276 |
Writing & Preference Grok-2 (Dec 2024) leads
GPT-4o mini: 39.5 (#248), Grok-2 (Dec 2024): 48.6 (#198)
| Benchmark | GPT-4o mini | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1286 | 1305 |
| LMArena Creative Writing | 1268 | 1284 |
| Short-Story Creative Writing | 67.2% | 63.6% |
| LMArena Multi-Turn | 1285 | 1290 |
| LiveBench Language | 28.6% | 45.6% |
| EQ-Bench Creative Writing | 873 | — |
| WildBench | 79.1% | — |
Frequently asked questions
Is GPT-4o mini better than Grok-2 (Dec 2024)?
Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 25.5 on the Noometry Index.
Is GPT-4o mini or Grok-2 (Dec 2024) better for coding?
Grok-2 (Dec 2024) scores higher on coding benchmarks: 33.3 versus 22.0 in the Noometry coding category.
How many benchmarks do GPT-4o mini and Grok-2 (Dec 2024) share?
33 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Grok-2 (Dec 2024) has 34.