Model comparison
DeepSeek Coder 33B vs Mercury 2.5
Mercury 2.5 has enough public results to be ranked (#242); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
DeepSeekSummary
- DeepSeek Coder 33B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek Coder 33B | Mercury 2.5 | |
|---|---|---|
| Provider | DeepSeek | Inception |
| Noometry Index | 38.9 | 33.5 |
| Released | 2023-11-02 | 2026-09-08 |
| Weights | Open | Proprietary |
| Context window | — | 260K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.04 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 9 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2.5 leads
DeepSeek Coder 33B: 38.0 (#184), Mercury 2.5: 39.5 (#156)
| Benchmark | DeepSeek Coder 33B | Mercury 2.5 |
|---|---|---|
| SciCode | — | 38.5% |
| BigCodeBench Instruct | 42% | — |
| BigCodeBench Complete | 51.1% | — |
| ALE-Bench | — | 301.65 |
| HumanEval+ | 75% | — |
| MBPP+ | 70.1% | — |
Reasoning Not comparable
DeepSeek Coder 33B: —, Mercury 2.5: 22.4 (#193)
| Benchmark | DeepSeek Coder 33B | Mercury 2.5 |
|---|---|---|
| CritPt | — | 0% |
| Epoch Capabilities Index | 96.32 | — |
| WinoGrande | 62% | — |
Math Not comparable
DeepSeek Coder 33B: —, Mercury 2.5: 23.3 (#272)
| Benchmark | DeepSeek Coder 33B | Mercury 2.5 |
|---|---|---|
| ProofBench | — | 3% |
| GSM8K | 35.4% | — |
Knowledge Not comparable
DeepSeek Coder 33B: —, Mercury 2.5: —
| Benchmark | DeepSeek Coder 33B | Mercury 2.5 |
|---|---|---|
| ARC (AI2) Challenge | 42.2% | — |
| MMLU | 39.4% | — |
Frequently asked questions
Is DeepSeek Coder 33B better than Mercury 2.5?
Mercury 2.5 has enough public results to be ranked (#242); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 33B or Mercury 2.5 better for coding?
Mercury 2.5 scores higher on coding benchmarks: 39.5 versus 38.0 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 33B and Mercury 2.5 share?
0 benchmarks have published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and Mercury 2.5 has 4.