nex-agi/nex-n2.5-mini
Nex AGIvia OpenRouter- average±5.0 (95%)
- 47.6
- leaderboard rankof 114
- ≈103
- benchmarksof 12
- 12
- per 1,000 documentsmean over its benchmarks
- $1.20
- seconds per inputmean response time
- 301.4
By task
-
Data correction
48.7
Best of 114 models with all its benchmarks: claude-opus-5-5, 82.7.
-
Document understanding
59.7
Best of 107 models with all its benchmarks: gpt-6-astra, 97.0.
-
Information extraction
55.9
Best of 107 models with all its benchmarks: grok-4.6, 90.8.
-
Transcription
31.7
Best of 114 models with all its benchmarks: gemini-4-argon, 96.2.
By benchmark
| Benchmark | ScoreThe best current run on each benchmark, on the benchmark's metric scaled to 0–100. ± is the 95% sampling margin, from resampling the run's inputs. | RankRank among all current models on that benchmark; ≈ for models that cannot be told apart within sampling error. | Per 1,000 docs | s / input | Best run |
|---|---|---|---|---|---|
| Bibliographic Dataother prompt | 56.3±39.5 | ≈103of 115 | $0.92$0.005 run | 149.42 | T2194 · 25 Oct 2026prompt_v2.txt |
| Blacklist Cards | 84.2±3.8 | ≈89of 114 | $0.19$0.006 run | 24.89 | T2201 · 25 Oct 2026prompt.txt |
| Book Advert XML Repairother prompt | 15.8±7.6 | ≈89of 119 | $1.15$0.057 run | 199.6 | T2203 · 25 Oct 2026prompt_v2.txt |
| Business Letters | 58.0±7.3 | ≈24of 114 | $0.39$0.022 run | 75.58 | T2195 · 25 Oct 2026prompt.txt |
| Company Listsother prompt | 50.3±20.1 | ≈105of 114 | $0.92$0.014 run | 168.15 | T2202 · 25 Oct 2026prompt_v2.txt |
| Duty Rosters | 29.1±18.2 | ≈96of 107 | $5.27$0.11 run | 1839.73 | T2207 · 25 Oct 2026prompt.txt |
| Fraktur Adverts | 0.0±0.0 | ≈108of 114 | $0.79$0.004 run | 161.85 | T2198 · 25 Oct 2026prompt_optimized.txt |
| General Meeting Minutes | 32.6±22.5 | ≈103of 108 | $2.09$0.019 run | 419.76 | T2206 · 25 Oct 2026prompt.txt |
| Library Cardsother prompt | 80.9±2.0 | ≈90of 114 | $0.16$0.042 run | 57.11 | T2199 · 25 Oct 2026prompt_year-string.txt |
| Magazine Pagesother prompt | 68.5±12.9 | ≈34of 115 | $0.59$0.027 run | 137.24 | T2205 · 25 Oct 2026prompt_explicit-json.txt |
| Medieval Manuscripts | 13.5±18.0 | ≈107of 114 | $1.41$0.017 run | 279.37 | T2200 · 25 Oct 2026prompt.txt |
| Personnel Cards | 81.7±12.4 | ≈94of 114 | $0.53$0.032 run | 104.5 | T2204 · 25 Oct 2026prompt.txt |
Price
| From | Input, $ per million tokens | Output, $ per million tokens | Source |
|---|---|---|---|
| 24 Oct 2026 | 0.025 | 0.1 | archived price page |
Every run
- T2207Duty Rosters25 Oct 202629.1$0.11
- T2206General Meeting Minutes25 Oct 202632.6$0.019
- T2205Magazine Pages25 Oct 202668.5$0.027
- T2204Personnel Cards25 Oct 202681.7$0.032
- T2203Book Advert XML Repair25 Oct 202615.8$0.057
- T2202Company Lists25 Oct 202650.3$0.014
- T2201Blacklist Cards25 Oct 202684.2$0.006
- T2200Medieval Manuscripts25 Oct 202613.5$0.017
- T2199Library Cards25 Oct 202680.9$0.042
- T2198Fraktur Adverts25 Oct 20260.0$0.004
- T2197Business Letters25 Oct 2026 · 32 signed letters54.0$0.014
- T2196Business Letters25 Oct 2026 · 25 unsigned letters54.0$0.005
- T2195Business Letters25 Oct 2026 · all 57 letters58.0$0.022
- T2194Bibliographic Data25 Oct 202656.3$0.005