# DBRX vs GPT-5.5

> GPT-5.5 is the stronger model overall, scoring 63.4 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/dbrx-vs-gpt-5-5
- Last updated: 2026-10-11
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. DBRX scores higher in 0 categories and GPT-5.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.5 leads 81.7 to 24.3.
- The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 94% for GPT-5.5.
- DBRX has downloadable open weights; the other is API-only.

## Snapshot

| | DBRX | GPT-5.5 |
|---|---|---|
| Provider | Databricks | OpenAI |
| Noometry Index | 29.4 | 63.4 |
| Rank | 311 | 9 |
| Context | — | 1.05M |
| Input $/M | — | $5 |
| Output $/M | — | $30 |
| Weights | Open | Proprietary |

## Coding

- DBRX: 32.9 (#266)
- GPT-5.5: 58.2 (#17)

| Benchmark | DBRX | GPT-5.5 |
|---|---|---|
| LMArena Coding | 1132 | 1494 |
| SWE-bench Verified | — | 80.6% |
| DeepSWE | — | 67% |
| FrontierCode | — | 43% |
| LMArena WebDev | — | 1513 |
| SciCode | — | 56.1% |
| GSO | — | 40.2% |
| WeirdML | — | 84.9% |
| MirrorCode | — | 10% |
| ALE-Bench | — | 1,943 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |

## Agentic & Tool Use

- DBRX: —
- GPT-5.5: 50.7 (#6)

| Benchmark | DBRX | GPT-5.5 |
|---|---|---|
| Terminal-Bench | — | 84.7% |
| APEX-Agents | — | 55.1% |
| OSWorld 2.0 | — | 13% |
| Remote Labor Index | — | 6.3% |
| τ²-bench Banking | — | 44.6% |
| DeepResearch Bench | — | 54% |
| PostTrainBench | — | 27.2% |
| ExploitBench | — | 47.4% |
| GBAEval | — | 53.2% |
| GDP.pdf | — | 26% |
| LMArena Search | — | 1242 |
| Vending-Bench 2 | — | 7,524 |

## Reasoning

- DBRX: 21.4 (#222)
- GPT-5.5: 72.8 (#11)

| Benchmark | DBRX | GPT-5.5 |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1489 |
| ARC-AGI-2 | — | 85% |
| SimpleBench | — | 69% |
| Kagi LLM Benchmark | — | 88.8% |
| NYT Connections (extended) | — | 96.2% |
| ARC-AGI-1 | — | 95% |
| CritPt | — | 27.1% |
| Chess Puzzles | — | 54% |
| EBR-Bench | — | 34.3% |
| Mystery Game Puzzles | — | 56% |
| DTBench | — | 96% |
| LMCA | — | 54.3% |
| Surface Evolver Bench | — | 88.1% |
| Bench to the Future 3 | — | 0.14 |
| Epoch Capabilities Index | — | 159.1 |
| ForecastBench | — | 60.6 |

## Math

- DBRX: 24.3 (#269)
- GPT-5.5: 81.7 (#11)

| Benchmark | DBRX | GPT-5.5 |
|---|---|---|
| LMArena Math | 1145 | 1486 |
| FrontierMath (Tiers 1-3) | — | 85.3% |
| FrontierMath Tier 4 | — | 72.5% |
| MathArena Final-Answer Competitions | — | 94.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 50% |
| MATH Level 5 | 11.7% | — |
| FrontierMath (Feb 2025 set) | — | 51.7% |
| FrontierMath Erdős | — | 0% |
| FrontierMath Tier 4 (v1) | — | 35.4% |

## Knowledge

- DBRX: 14.9 (#294)
- GPT-5.5: 64.4 (#17)

| Benchmark | DBRX | GPT-5.5 |
|---|---|---|
| GPQA Diamond | 32.9% | 94% |
| LMArena Expert | 1076 | 1508 |
| SimpleQA Verified | — | 63% |
| Vectara Hallucination Rate | — | 9.3% |

## Multimodal

- DBRX: —
- GPT-5.5: 46.9 (#12)

| Benchmark | DBRX | GPT-5.5 |
|---|---|---|
| LMArena Vision | — | 1297 |
| Blueprint-Bench 2 | — | 36.2% |
| Furniture Assembly | — | 44.2% |
| LMArena Document | — | 1486 |

## Multilingual

- DBRX: 29.3 (#268)
- GPT-5.5: 56.4 (#20)

| Benchmark | DBRX | GPT-5.5 |
|---|---|---|
| LMArena Non-English | 1071 | 1467 |
| LMArena Chinese | 1068 | 1533 |
| LMArena French | 1096 | 1486 |
| LMArena German | 1057 | 1480 |
| LMArena Japanese | 990 | 1498 |
| LMArena Korean | 993 | 1460 |
| LMArena Russian | 1078 | 1473 |
| LMArena Spanish | 1064 | 1468 |

## Instruction Following

- DBRX: 57.5 (#270)
- GPT-5.5: 77.5 (#18)

| Benchmark | DBRX | GPT-5.5 |
|---|---|---|
| LMArena Instruction Following | 1112 | 1479 |

## Long Context

- DBRX: 33.7 (#258)
- GPT-5.5: 48.3 (#12)

| Benchmark | DBRX | GPT-5.5 |
|---|---|---|
| LMArena Longer Query | 1112 | 1484 |
| CL-bench Life | — | 22.2% |

## Writing & Preference

- DBRX: 33.6 (#275)
- GPT-5.5: 72.7 (#13)

| Benchmark | DBRX | GPT-5.5 |
|---|---|---|
| LMArena Text | 1119 | 1472 |
| LMArena Creative Writing | 1104 | 1455 |
| LMArena Multi-Turn | 1111 | 1476 |
| EQ-Bench Creative Writing | — | 1844 |
| EQ-Bench 4 | — | 1315 |

## FAQ

### Is DBRX better than GPT-5.5?

GPT-5.5 is the stronger model overall, scoring 63.4 to 29.4 on the Noometry Index.

### Is DBRX or GPT-5.5 better for coding?

GPT-5.5 scores higher on coding benchmarks: 58.2 versus 32.9 in the Noometry coding category.

### How many benchmarks do DBRX and GPT-5.5 share?

18 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and GPT-5.5 has 71.