Composer 2.5
CursorKey composer-2.5Also reported as cursor/composer-2.5, combo/composer-2.5, xai/composer-2.5, cu/composer-2.5
- Rank
- #113
- by active users
- Active users
- 9
- Down 18 from 27 active users in the previous 30 days. vs previous 30 days
- Adoption
- 0.9%
- of 956 accounts
- Tokens
- 1.2B
- cache included
- Est. cost
- $270
- at public list prices
- First seen
- May 18, 2026
- in any submission
Oct 15 – Nov 13, 2026 (UTC)956 accounts100% of tokens from an identified modelData through Nov 13, 2026, 01:06 UTCHow we count
Daily active users
Distinct accounts that used this model on each UTC day.
0 active users on Nov 13, 2026
Show daily values
| Date (UTC) | Active users | Tokens |
|---|---|---|
| Oct 15, 2026 | 2 | 10.6M |
| Oct 16, 2026 | 2 | 575K |
| Oct 17, 2026 | 1 | 340K |
| Oct 18, 2026 | 1 | 28.1M |
| Oct 19, 2026 | 0 | 0 |
| Oct 20, 2026 | 2 | 7.4M |
| Oct 21, 2026 | 1 | 56.4K |
| Oct 22, 2026 | 2 | 6.6M |
| Oct 23, 2026 | 2 | 3.2M |
| Oct 24, 2026 | 0 | 0 |
| Oct 25, 2026 | 1 | 422K |
| Oct 26, 2026 | 1 | 6.3M |
| Oct 27, 2026 | 2 | 9M |
| Oct 28, 2026 | 0 | 0 |
| Oct 29, 2026 | 1 | 937K |
| Oct 30, 2026 | 0 | 0 |
| Oct 31, 2026 | 0 | 0 |
| Nov 1, 2026 | 0 | 0 |
| Nov 2, 2026 | 1 | 270.9M |
| Nov 3, 2026 | 2 | 415.3M |
| Nov 4, 2026 | 2 | 238.9M |
| Nov 5, 2026 | 1 | 133.5M |
| Nov 6, 2026 | 1 | 11.6M |
| Nov 7, 2026 | 1 | 11.8M |
| Nov 8, 2026 | 0 | 0 |
| Nov 9, 2026 | 0 | 0 |
| Nov 10, 2026 | 1 | 469K |
| Nov 11, 2026 | 1 | 1.4M |
| Nov 12, 2026 | 1 | 3.8M |
| Nov 13, 2026 | 0 | 0 |
Token mix
How the 1.2B tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.
- Input6.2%
- Output0.5%
- Cache read93%
- Cache write0%
- Reasoning0%
Agents that carry Composer 2.5
Each agent's share of this model's tokens, and how many accounts used the model through it.
Cursor78% of this model's tokens6active users
Oh My Pi14% of this model's tokens3active users
Pi8.2% of this model's tokens1active users
Grok Build<0.1% of this model's tokens1active users
Benchmarks
The best result for Composer 2.5 in each benchmark Tokscale tracks. Each benchmark has its own unit, run conditions and source, so compare a score only with other models on the same benchmark. Rank is among the models Tokscale matched in that benchmark.
- CursorBenchAgentic coding · Cursor, collected by Epoch AI27.7%
CursorBench: 27.7%
- Model
- Composer 2.5
- Listed as
- Composer 2.5
- Conditions
- Not reported
- Unit
- score
- Model released
- May 18, 2026
- Retrieved
- Nov 12, 2026
Source · CursorBench results by Cursor, collected by Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
Rank #21 of 21 matched modelsNo conditions reportedModel released May 18, 2026Source: cursor.com (opens in a new tab)
Pricing
models.dev does not list Composer 2.5, so Tokscale has no list price or price estimate for it.
Specs
models.dev does not list Composer 2.5, so Tokscale has no specs for it.
Top public profiles
Public profiles that used Composer 2.5 most in this period, by tokens. Hidden accounts are never listed.
- 1
registered2nd@registered2nd847.5Mtokens$185est. cost3active days$185 est. cost · 3 active days
- 2
Nehr@AgileInnov8tor240.1Mtokens$64est. cost8active days$64 est. cost · 8 active days
- 3
季悠然@youranreus34.3Mtokens$9est. cost2active days$9 est. cost · 2 active days
- 4
Muhammad Abdullah@iAbdullahMughal12.2Mtokens$3est. cost8active days$3 est. cost · 8 active days
- 5
Yags@whyyagswhy9.8Mtokens$5est. cost1active days$5 est. cost · 1 active days
- 6
iz@islee235208.2Mtokens$2est. cost1active days$2 est. cost · 1 active days
- 7
candyandy@andredubbs7.3Mtokens$2est. cost2active days$2 est. cost · 2 active days
- 8
Jason Sher@jslabxyz1.7Mtokens<$1est. cost3active days<$1 est. cost · 3 active days
- 9
barramhong@hong798098tokens<$1est. cost1active days<$1 est. cost · 1 active days
More from Cursor
Other Cursor models in the same period, by active users.
- Composer 2.5 Fast1.5% adoption14active users
Sources and attribution
Each score keeps its own source, unit and run conditions. Tokscale does not combine benchmarks into one score, and a missing score means the model was not evaluated, not that it scored zero.