Model comparison
GPT-5.2 Codex vs Grok 4.3
Grok 4.3 is the stronger model overall, scoring 43.8 to 42.6 on the Noometry Index.
Last verified . 2 shared benchmarks.
Summary
- They share 2 benchmarks with published results for both. GPT-5.2 Codex scores higher in 2 categories and Grok 4.3 in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-5.2 Codex leads 41.0 to 27.7.
- Grok 4.3 is cheaper at $1.25 / $2.50 per million input/output tokens, against $1.75 / $14 for GPT-5.2 Codex.
- Grok 4.3 accepts more context: 1M tokens versus 400K.
Side by side
| GPT-5.2 Codex | Grok 4.3 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 42.6 | 43.8 |
| Released | 2025-12-18 | 2026-04-17 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1M |
| Max output | 128K | 30K |
| Input $ / M tokens | $1.75 | $1.25 |
| Output $ / M tokens | $14 | $2.50 |
| Results tracked | 5 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.2 Codex leads
GPT-5.2 Codex: 45.5 (#71), Grok 4.3: 41.6 (#121)
| Benchmark | GPT-5.2 Codex | Grok 4.3 |
|---|---|---|
| LMArena WebDev | 1339 | 1357 |
| ALE-Bench | 1,300 | 944.17 |
| SWE-bench Verified (bash only) | 72.8% | — |
| SWE-bench Multilingual | 66.3% | — |
| SciCode | — | 47.3% |
| WeirdML | — | 49.9% |
| LMArena Coding | — | 1415 |
Agentic & Tool Use GPT-5.2 Codex leads
GPT-5.2 Codex: 41.0 (#22), Grok 4.3: 27.7 (#99)
| Benchmark | GPT-5.2 Codex | Grok 4.3 |
|---|---|---|
| Terminal-Bench | 66.5% | — |
| GDP.pdf | — | 8% |
| LMArena Search | — | 1165 |
| Vending-Bench 2 | — | 35.26 |
Reasoning Not comparable
GPT-5.2 Codex: —, Grok 4.3: 35.9 (#68)
| Benchmark | GPT-5.2 Codex | Grok 4.3 |
|---|---|---|
| NYT Connections (extended) | — | 55.2% |
| CritPt | — | 8% |
| Chess Puzzles | — | 25% |
| LMArena Hard Prompts | — | 1396 |
| DTBench | — | 90.7% |
| LMCA | — | 38.3% |
| Epoch Capabilities Index | — | 149.16 |
| ForecastBench | — | 60.3 |
Math Not comparable
GPT-5.2 Codex: —, Grok 4.3: 46.0 (#74)
| Benchmark | GPT-5.2 Codex | Grok 4.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 42.8% |
| FrontierMath Tier 4 | — | 14.6% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| ProofBench | — | 11% |
| LMArena Math | — | 1388 |
Knowledge Not comparable
GPT-5.2 Codex: —, Grok 4.3: 52.5 (#62)
| Benchmark | GPT-5.2 Codex | Grok 4.3 |
|---|---|---|
| GPQA Diamond | — | 88.8% |
| SimpleQA Verified | — | 33.2% |
| LMArena Expert | — | 1385 |
Multimodal Not comparable
GPT-5.2 Codex: —, Grok 4.3: 31.6 (#104)
| Benchmark | GPT-5.2 Codex | Grok 4.3 |
|---|---|---|
| LMArena Vision | — | 1229 |
| Blueprint-Bench 2 | — | 0% |
Multilingual Not comparable
GPT-5.2 Codex: —, Grok 4.3: 50.5 (#120)
| Benchmark | GPT-5.2 Codex | Grok 4.3 |
|---|---|---|
| LMArena Non-English | — | 1385 |
| LMArena Chinese | — | 1422 |
| LMArena French | — | 1412 |
| LMArena German | — | 1395 |
| LMArena Japanese | — | 1379 |
| LMArena Korean | — | 1356 |
| LMArena Russian | — | 1399 |
| LMArena Spanish | — | 1398 |
Instruction Following Not comparable
GPT-5.2 Codex: —, Grok 4.3: 72.1 (#140)
| Benchmark | GPT-5.2 Codex | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | — | 1366 |
Long Context Not comparable
GPT-5.2 Codex: —, Grok 4.3: 42.5 (#123)
| Benchmark | GPT-5.2 Codex | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | — | 1393 |
Writing & Preference Not comparable
GPT-5.2 Codex: —, Grok 4.3: 58.5 (#118)
| Benchmark | GPT-5.2 Codex | Grok 4.3 |
|---|---|---|
| LMArena Text | — | 1397 |
| LMArena Creative Writing | — | 1380 |
| EQ-Bench 4 | — | 1075 |
| LMArena Multi-Turn | — | 1406 |
Frequently asked questions
Is GPT-5.2 Codex better than Grok 4.3?
Grok 4.3 is the stronger model overall, scoring 43.8 to 42.6 on the Noometry Index.
Which is cheaper, GPT-5.2 Codex or Grok 4.3?
Grok 4.3 is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; GPT-5.2 Codex lists at $1.75 and $14.
Is GPT-5.2 Codex or Grok 4.3 better for coding?
GPT-5.2 Codex scores higher on coding benchmarks: 45.5 versus 41.6 in the Noometry coding category.
Which has the bigger context window?
Grok 4.3 does, with 1M tokens against 400K.
How many benchmarks do GPT-5.2 Codex and Grok 4.3 share?
2 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Grok 4.3 has 40.