GPT-5 Mini vs Nemotron 3 Ultra
GPT-5 Mini leads Nemotron 3 Ultra on coding, 34.2 to 30.0 on the Vibe Coding Index, and GPT-5 Mini costs 1.2x less per output token ($2.00 vs $2.40 per million). Updated October 23, 2026; 60 benchmarks have a result for both.
GPT-5 Mini or Nemotron 3 Ultra: which to pick
Pick GPT-5 Mini for coding: it scores 34.2 on the Vibe Coding Index against 30.0 for Nemotron 3 Ultra, though on 2 benchmarks against 3.
Pick Nemotron 3 Ultra for work measured by SWE-bench Verified (Vals AI) or SciCode, where it leads.
- Shared results
- 60
- GPT-5 Mini only
- 43
- Nemotron 3 Ultra only
- 11
- Like-for-like categories
- 8 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
GPT-5 Mini
GPT-5 Mini scores 34.2 against 30.0.
2 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
Nemotron 3 Ultra
Nemotron 3 Ultra leads, 22.9 against 20.6.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Nemotron 3 Ultra has a AA Agentic Index result, 20.1.
Directional only
Reasoning
GPQA Diamond
Nemotron 3 Ultra
Nemotron 3 Ultra leads, 86.1% against 80.3%.
Same board, both measured
Math
AIME
No call
Only GPT-5 Mini has a AIME result, 91.5%.
Directional only
Knowledge
MMLU Pro
Nemotron 3 Ultra
Nemotron 3 Ultra leads, 85.8% against 82.2%.
Same board, both measured
Web design
Design Arena: websites
Nemotron 3 Ultra
Nemotron 3 Ultra leads, 1145 against 1125.
Same board, both measured
Long documents
Listed context window
GPT-5 Mini
GPT-5 Mini takes 400K tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-5 Mini
GPT-5 Mini $0.0013, Nemotron 3 Ultra $0.0018 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5 Mini has the number, $0.08.
Directional only
At a glance
- Coding index
- GPT-5 Mini 34.2 from 2 benchmarks, Nemotron 3 Ultra 30.0 from 3 benchmarks.
- Widest category
- Agentic work, 12.3 points apart on average over 1 shared benchmark.
- Widest single gap
- LMArena Text: Chinese: GPT-5 Mini 1385 against Nemotron 3 Ultra 1498, 18.7 points apart on a 0 to 100 scale.
- Output price
- GPT-5 Mini $2.00 against Nemotron 3 Ultra $2.40 per million output tokens, 1.2x apart.
- Context window
- GPT-5 Mini takes 400K tokens, Nemotron 3 Ultra 262K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | GPT-5 Mini | Bars | Nemotron 3 Ultra | Ties |
|---|---|---|---|---|
| Coding | 3 | 5 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 8 | ||
| Math | 1 | 2 | 1 tie | |
| Knowledge | 2 | 7 | ||
| Web design | 2 | 6 | ||
| General | 0 | 20 | ||
| All shared boards | 8 | 51 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index35
| Benchmark | GPT-5 Mini | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| SWE-bench Verified | 59.8% | Not measured | Only GPT-5 Mini measured |
| SWE-bench Multilingual | 39.7% | Not measured | Only GPT-5 Mini measured |
| AA Coding Index | Not measured | 49.3 | Only Nemotron 3 Ultra measured |
| LiveCodeBench (Vals AI) | 86.6% | 86.0% | GPT-5 Mini |
| SWE-bench Verified (Vals AI) | 60.8% | 69.0% | Nemotron 3 Ultra |
| Vibe Code Bench (Vals AI) | 14.2% | 7.6% | GPT-5 Mini |
| Code migration (Vals AI) | Not measured | 4.9% | Only Nemotron 3 Ultra measured |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only Nemotron 3 Ultra measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 50.9% | Only Nemotron 3 Ultra measured |
| LiveCodeBench (Artificial Analysis run) | 83.8% | Not measured | Only GPT-5 Mini measured |
| SciCode | 39.0% | 40.3% | Nemotron 3 Ultra |
| Terminal-Bench Hard (Artificial Analysis run) | 33.3% | 36.4% | Nemotron 3 Ultra |
| Terminal-Bench | 34.8% | Not measured | Only GPT-5 Mini measured |
| FrontierCode | Not measured | 13.6% | Only Nemotron 3 Ultra measured |
| WeirdML | 52.7% | 43.5% | GPT-5 Mini |
| LMArena Text: coding | 1406 | 1467 | Nemotron 3 Ultra |
| LMArena Text: software and IT | 1394 | 1468 | Nemotron 3 Ultra |
| Neither model has a result on the other 26 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-5 Mini | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| AA Intelligence Index | 20.6 | 22.9 | Nemotron 3 Ultra |
| Epoch Capabilities Index | 145.3 | 146.0 | Nemotron 3 Ultra |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-5 Mini | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 20.1 | Only Nemotron 3 Ultra measured |
| Finance Agent (Vals AI) | Not measured | 37.7% | Only Nemotron 3 Ultra measured |
| Legal Research Bench (Vals AI) | Not measured | 15.4% | Only Nemotron 3 Ultra measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 31.7% | Only Nemotron 3 Ultra measured |
| τ²-Bench Telecom | 71.1% | 83.3% | Nemotron 3 Ultra |
| APEX-Agents | Not measured | 22.7% | Only Nemotron 3 Ultra measured |
| Vending-Bench 2 | -$31 | Not measured | Only GPT-5 Mini measured |
| Berkeley Function Calling Leaderboard (BFCL) | 55.5% | Not measured | Only GPT-5 Mini measured |
| MCP Atlas | Not measured | 63.1% | Only Nemotron 3 Ultra measured |
| Neither model has a result on the other 33 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | GPT-5 Mini | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| GPQA Diamond | 80.3% | 86.1% | Nemotron 3 Ultra |
| MMMU Pro (Vals AI) | 78.9% | Not measured | Only GPT-5 Mini measured |
| GPQA Diamond (Artificial Analysis run) | 82.8% | 86.7% | Nemotron 3 Ultra |
| Humanity's Last Exam (Artificial Analysis run) | 21.5% | 28.4% | Nemotron 3 Ultra |
| GPQA Diamond (Epoch AI run) | 75.0% | 85.4% | Nemotron 3 Ultra |
| ARC-AGI | 54.3% | Not measured | Only GPT-5 Mini measured |
| ARC-AGI-2 | 4.4% | Not measured | Only GPT-5 Mini measured |
| Chess puzzles | 24.0% | Not measured | Only GPT-5 Mini measured |
| Mystery game puzzles | 10.0% | 20.0% | Nemotron 3 Ultra |
| VPCT | 40.2% | Not measured | Only GPT-5 Mini measured |
| LMArena Text: hard prompts | 1380 | 1452 | Nemotron 3 Ultra |
| LMArena Text: expert | 1379 | 1472 | Nemotron 3 Ultra |
| LMArena Text: hard prompts in English | 1383 | 1453 | Nemotron 3 Ultra |
| LMArena Vision: diagrams | 1202 | Not measured | Only GPT-5 Mini measured |
| LMArena Vision: homework | 1210 | Not measured | Only GPT-5 Mini measured |
| Kagi LLM Benchmark | 70.3% | Not measured | Only GPT-5 Mini measured |
| Neither model has a result on the other 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | GPT-5 Mini | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| AIME | 91.5% | Not measured | Only GPT-5 Mini measured |
| MATH 500 (Vals AI) | 94.8% | Not measured | Only GPT-5 Mini measured |
| MGSM (Vals AI) | 92.6% | Not measured | Only GPT-5 Mini measured |
| AA Math Index | 90.7 | Not measured | Only GPT-5 Mini measured |
| AIME 2025 (Artificial Analysis run) | 90.7% | Not measured | Only GPT-5 Mini measured |
| OTIS Mock AIME | 86.7% | 86.7% | Tie |
| FrontierMath, tiers 1 to 3 | 46.7% | Not measured | Only GPT-5 Mini measured |
| FrontierMath, tier 4 | 12.2% | Not measured | Only GPT-5 Mini measured |
| ProofBench | 9.0% | 2.0% | GPT-5 Mini |
| MATH level 5 | 97.8% | Not measured | Only GPT-5 Mini measured |
| LMArena Text: math | 1378 | 1457 | Nemotron 3 Ultra |
| LMArena Text: mathematical work | 1380 | 1462 | Nemotron 3 Ultra |
| MathArena | 14.8% | Not measured | Only GPT-5 Mini measured |
| Neither model has a result on the other 1 board here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index27
| Benchmark | GPT-5 Mini | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| MMLU Pro | 82.2% | 85.8% | Nemotron 3 Ultra |
| LegalBench (Vals AI) | 81.8% | 82.1% | Nemotron 3 Ultra |
| CaseLaw (Vals AI) | 68.5% | Not measured | Only GPT-5 Mini measured |
| CorpFin (Vals AI) | 60.2% | 65.5% | Nemotron 3 Ultra |
| TaxEval (Vals AI) | 75.2% | 73.1% | GPT-5 Mini |
| MortgageTax (Vals AI) | 66.9% | Not measured | Only GPT-5 Mini measured |
| MedQA (Vals AI) | 96.1% | Not measured | Only GPT-5 Mini measured |
| MedCode (Vals AI) | 43.0% | 38.6% | GPT-5 Mini |
| MMLU Pro (Artificial Analysis run) | 83.7% | Not measured | Only GPT-5 Mini measured |
| SimpleQA Verified | 21.6% | Not measured | Only GPT-5 Mini measured |
| LMArena Text: science | 1371 | 1465 | Nemotron 3 Ultra |
| LMArena Text: medicine and healthcare | 1380 | 1455 | Nemotron 3 Ultra |
| LMArena Text: legal and government | 1375 | 1453 | Nemotron 3 Ultra |
| LMArena Text: business and finance | 1358 | 1435 | Nemotron 3 Ultra |
| FACTS Benchmark Suite | 38.6% | Not measured | Only GPT-5 Mini measured |
| Neither model has a result on the other 5 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index26
| Benchmark | GPT-5 Mini | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| Design Arena: websites | 1125 | 1145 | Nemotron 3 Ultra |
| Design Arena: UI components | 1103 | 1135 | Nemotron 3 Ultra |
| Design Arena: game dev | 1129 | 1138 | Nemotron 3 Ultra |
| Design Arena: data viz | 1131 | 1142 | Nemotron 3 Ultra |
| Design Arena: 3D | 1038 | 1132 | Nemotron 3 Ultra |
| Design Arena: all code categories | 1114 | 1146 | Nemotron 3 Ultra |
| Design Arena: SVG | 1091 | 1069 | GPT-5 Mini |
| Design Arena: ASCII art | 1125 | 1100 | GPT-5 Mini |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index020
| Benchmark | GPT-5 Mini | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 43.0% | Not measured | Only GPT-5 Mini measured |
| MedScribe (Vals AI) | 80.6% | Not measured | Only GPT-5 Mini measured |
| IFBench | 75.4% | 81.4% | Nemotron 3 Ultra |
| Long context reasoning (AA-LCR) | 72.3% | 79.3% | Nemotron 3 Ultra |
| DTBench | 80.5% | 90.1% | Nemotron 3 Ultra |
| LMCA | 34.2% | 36.9% | Nemotron 3 Ultra |
| Fiction.LiveBench | 69.4% | Not measured | Only GPT-5 Mini measured |
| Creative writing (Lech Mazur) | 83.1% | Not measured | Only GPT-5 Mini measured |
| LMArena Text | 1373 | 1445 | Nemotron 3 Ultra |
| LMArena Text: instruction following | 1357 | 1418 | Nemotron 3 Ultra |
| LMArena Text: creative writing | 1325 | 1398 | Nemotron 3 Ultra |
| LMArena Vision | 1202 | Not measured | Only GPT-5 Mini measured |
| LMArena Text: English | 1379 | 1454 | Nemotron 3 Ultra |
| LMArena Text: non-English | 1363 | 1427 | Nemotron 3 Ultra |
| LMArena Text: Chinese | 1385 | 1498 | Nemotron 3 Ultra |
| LMArena Text: German | 1366 | 1474 | Nemotron 3 Ultra |
| LMArena Text: Japanese | 1341 | Not measured | Only GPT-5 Mini measured |
| LMArena Text: Korean | 1306 | 1385 | Nemotron 3 Ultra |
| LMArena Text: French | 1386 | 1473 | Nemotron 3 Ultra |
| LMArena Text: Spanish | 1355 | 1454 | Nemotron 3 Ultra |
| LMArena Text: Russian | 1362 | 1417 | Nemotron 3 Ultra |
| LMArena Text: Polish | 1378 | 1385 | Nemotron 3 Ultra |
| LMArena Text: multi-turn | 1363 | 1411 | Nemotron 3 Ultra |
| LMArena Text: longer queries | 1355 | 1437 | Nemotron 3 Ultra |
| LMArena Text: writing and language | 1344 | 1405 | Nemotron 3 Ultra |
| LMArena Text: entertainment and media | 1340 | 1397 | Nemotron 3 Ultra |
| LMArena Vision: English | 1216 | Not measured | Only GPT-5 Mini measured |
| LMArena Vision: Chinese | 1214 | Not measured | Only GPT-5 Mini measured |
| LMArena Vision: reading text | 1199 | Not measured | Only GPT-5 Mini measured |
| LMArena Vision: humor | 1205 | Not measured | Only GPT-5 Mini measured |
| LMArena Vision: captioning | 1217 | Not measured | Only GPT-5 Mini measured |
| LMArena Vision: recognizing things | 1226 | Not measured | Only GPT-5 Mini measured |
| LMArena Vision: creative writing | 1181 | Not measured | Only GPT-5 Mini measured |
| MultiChallenge | 59.0% | Not measured | Only GPT-5 Mini measured |
| Neither model has a result on the other 14 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5 Mini | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
GPT-5 Mini costs less
Repository review
50K input + 3K output tokens
GPT-5 Mini costs less
Agent loop
200K input + 10K output tokens
GPT-5 Mini costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | OpenAI GPT-5 Mini | NVIDIA Nemotron 3 Ultra |
|---|---|---|
| Maker | OpenAI | NVIDIA |
| Weights | No public weights listed | Open weights |
| Released | August 7, 2025 | June 4, 2026 |
| Context window | 400K | 262K |
| Input $/Mtok | $0.25 | $0.60 |
| Output $/Mtok | $2.00 | $2.40 |
| Coding index | 34.2 | 30.0 |
| Independent measurements behind it | 2 | 3 |
| Cost per solved task | $0.08 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5 Mini better than Nemotron 3 Ultra for coding?
Pick GPT-5 Mini for coding: it scores 34.2 on the Vibe Coding Index against 30.0 for Nemotron 3 Ultra, though on 2 benchmarks against 3. Pick Nemotron 3 Ultra for work measured by SWE-bench Verified (Vals AI) or SciCode, where it leads.
Which is cheaper, GPT-5 Mini or Nemotron 3 Ultra?
GPT-5 Mini costs $0.25 per million input tokens and $2.00 per million output tokens; Nemotron 3 Ultra costs $0.60 and $2.40. Cost per solved task is known for GPT-5 Mini only.
Which has the bigger context window, GPT-5 Mini or Nemotron 3 Ultra?
GPT-5 Mini, with 400K tokens against 262K.
How many benchmarks is the GPT-5 Mini vs Nemotron 3 Ultra comparison based on?
60 benchmarks have a result for both models as of October 23, 2026. GPT-5 Mini's coding index rests on 2 independent benchmarks and Nemotron 3 Ultra's on 3. Where only one model has a result, the page says so instead of naming a winner.