Model comparison
DeepSeek-V2.5 (Sep 2024) vs Grok 4.5
Grok 4.5 is the stronger model overall, scoring 55.0 to 37.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and Grok 4.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.5 leads 56.0 to 24.5.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Grok 4.5 | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 37.0 | 55.0 |
| Released | 2024-09-06 | 2026-07-08 |
| Weights | Open | Proprietary |
| Context window | — | 500K |
| Max output | — | 500K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 22 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.5 leads
DeepSeek-V2.5 (Sep 2024): 31.3 (#274), Grok 4.5: 51.7 (#34)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.5 |
|---|---|---|
| LMArena Coding | 1310 | 1473 |
| DeepSWE | — | 53.8% |
| FrontierCode | — | 42.4% |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1552 |
| SciCode | — | 54.1% |
| WeirdML | — | 46.4% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 1,309 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, Grok 4.5: 44.4 (#15)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.5 |
|---|---|---|
| APEX-Agents | — | 56.2% |
| τ²-bench Banking | — | 47.9% |
| PostTrainBench | — | 23.4% |
| GBAEval | — | 65.4% |
| GDP.pdf | — | 14% |
| LMArena Search | — | 1213 |
| Vending-Bench 2 | — | 3,887 |
Reasoning Grok 4.5 leads
DeepSeek-V2.5 (Sep 2024): 24.5 (#145), Grok 4.5: 56.0 (#23)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.5 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1462 |
| ARC-AGI-2 | — | 52.6% |
| SimpleBench | — | 70% |
| Kagi LLM Benchmark | — | 83.5% |
| NYT Connections (extended) | — | 79.9% |
| ARC-AGI-1 | — | 87.2% |
| CritPt | — | 15.4% |
| Chess Puzzles | — | 36% |
| DTBench | — | 96.5% |
| LMCA | — | 45.2% |
| Surface Evolver Bench | — | 74.4% |
| Epoch Capabilities Index | — | 154.02 |
Math Grok 4.5 leads
DeepSeek-V2.5 (Sep 2024): 33.3 (#177), Grok 4.5: 60.7 (#29)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.5 |
|---|---|---|
| LMArena Math | 1289 | 1457 |
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 24.4% |
| OTIS Mock AIME 2024-2025 | — | 97.8% |
| ProofBench | — | 31% |
Knowledge Grok 4.5 leads
DeepSeek-V2.5 (Sep 2024): 34.2 (#190), Grok 4.5: 62.3 (#21)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.5 |
|---|---|---|
| LMArena Expert | 1266 | 1466 |
| GPQA Diamond | — | 93.4% |
| SimpleQA Verified | — | 48.3% |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, Grok 4.5: 37.8 (#63)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.5 |
|---|---|---|
| LMArena Vision | — | 1287 |
| Blueprint-Bench 2 | — | 27.3% |
| Furniture Assembly | — | 22.5% |
| LMArena Document | — | 1452 |
Multilingual Grok 4.5 leads
DeepSeek-V2.5 (Sep 2024): 42.7 (#188), Grok 4.5: 54.5 (#43)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.5 |
|---|---|---|
| LMArena Non-English | 1273 | 1439 |
| LMArena Chinese | 1317 | 1497 |
| LMArena French | 1288 | 1458 |
| LMArena German | 1258 | 1448 |
| LMArena Japanese | 1228 | 1425 |
| LMArena Korean | 1209 | 1402 |
| LMArena Russian | 1289 | 1447 |
| LMArena Spanish | 1248 | 1452 |
Instruction Following Grok 4.5 leads
DeepSeek-V2.5 (Sep 2024): 67.7 (#189), Grok 4.5: 76.3 (#45)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.5 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1446 |
Long Context Grok 4.5 leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#169), Grok 4.5: 44.8 (#54)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.5 |
|---|---|---|
| LMArena Longer Query | 1301 | 1463 |
Writing & Preference Grok 4.5 leads
DeepSeek-V2.5 (Sep 2024): 50.0 (#182), Grok 4.5: 65.9 (#40)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.5 |
|---|---|---|
| LMArena Text | 1294 | 1448 |
| LMArena Creative Writing | 1285 | 1442 |
| LMArena Multi-Turn | 1297 | 1457 |
| EQ-Bench Creative Writing | — | 1579 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Grok 4.5?
Grok 4.5 is the stronger model overall, scoring 55.0 to 37.0 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Grok 4.5 better for coding?
Grok 4.5 scores higher on coding benchmarks: 51.7 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Grok 4.5 share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Grok 4.5 has 52.