CursorBench
Cursor leaderboard on ambiguous, multi-file coding tasks taken from real Cursor sessions, with cost, tokens and agent steps per task.
At a glance
Gemini 4 Neon Extra High leads with 65.4%, out of 53 results. Best score for the money: Haiku 5.5 Max, 48.4% for $1.14 per task. Cursor designs both the tasks and the agent that runs them: the ranking reflects work inside Cursor, and the cost per task shows what a higher reasoning level costs for a few more points.
Value and speed are picked among the top 27, so a cheap or quick run with a low score never wins. Data retrieved on Nov 22, 2026.
- Configurations
- 53
- Best score
- 65.4%
- Gemini 4 Neon Extra High
- Lowest cost per task
- $0.080
- Haiku 5.5 Low · 27.8%
- Version
- 4.1
- Version Cursor names on its page
53 / 53 configurations
Cost / task: $10.67Tokens / task: 136,273Steps / task: 73
Cost / task: $6.54Tokens / task: 88,596Steps / task: 56
Cost / task: $8.52Tokens / task: 114,518Steps / task: 97
Cost / task: $8.09Tokens / task: 205,981Steps / task: 113
Cost / task: $48.11Tokens / task: 541,003Steps / task: 295
Cost / task: $7.22Tokens / task: 103,189Steps / task: 83
Cost / task: $17.84Tokens / task: 194,918Steps / task: 122
Cost / task: $11.88Tokens / task: 213,070Steps / task: 144
Cost / task: $3.07Tokens / task: 47,059Steps / task: 41
Cost / task: $4.57Tokens / task: 113,807Steps / task: 77
Cost / task: $6.54Tokens / task: 104,901Steps / task: 95
Cost / task: $10.51Tokens / task: 108,213Steps / task: 77
Cost / task: $9.14Tokens / task: 135,038Steps / task: 118
Cost / task: $7.64Tokens / task: 128,231Steps / task: 101
Cost / task: $8.64Tokens / task: 48,526Steps / task: 127
Cost / task: $3.87Tokens / task: 56,162Steps / task: 64
Cost / task: $8.63Tokens / task: 342,273Steps / task: 199
Cost / task: $5.01Tokens / task: 47,678Steps / task: 40
Cost / task: $4.26Tokens / task: 40,384Steps / task: 34
Cost / task: $2.85Tokens / task: 39,736Steps / task: 52
Cost / task: $3.13Tokens / task: 112,299Steps / task: 87
Cost / task: $10.19Tokens / task: 90,268Steps / task: 110
Cost / task: $1.14Tokens / task: 344,890Steps / task: 166
- #24Gemini 4 Argonlow47.9%
—
Cost / task: $7.96Tokens / task: 40,541Steps / task: 121
Cost / task: $1.28Tokens / task: 43,606Steps / task: 45
Cost / task: $6.88Tokens / task: 65,850Steps / task: 84
Cost / task: $1.26Tokens / task: 19,580Steps / task: 26
Cost / task: $0.56Tokens / task: 149,314Steps / task: 94
Cost / task: $5.26Tokens / task: 58,554Steps / task: 62
Cost / task: $1.41Tokens / task: 43,088Steps / task: 48
Cost / task: $1.43Tokens / task: 19,497Steps / task: 32
- #32Grok 4.7medium42.5%
—
Cost / task: $5.52Tokens / task: 41,173Steps / task: 70
Cost / task: $2.89Tokens / task: 56,572Steps / task: 113
Cost / task: $4.28Tokens / task: 46,330Steps / task: 52
Cost / task: $7.60Tokens / task: 40,466Steps / task: 100
Cost / task: $2.59Tokens / task: 26,374Steps / task: 40
Cost / task: $0.31Tokens / task: 77,196Steps / task: 61
Cost / task: $4.32Tokens / task: 23,921Steps / task: 58
Cost / task: $2.33Tokens / task: 47,142Steps / task: 96
Cost / task: $0.63Tokens / task: 19,144Steps / task: 26
Cost / task: $0.17Tokens / task: 43,441Steps / task: 41
Cost / task: $3Tokens / task: 16,319Steps / task: 44
Cost / task: $1.76Tokens / task: 16,863Steps / task: 33
- #44Muse Spark 1.3high32.1%
—
Cost / task: $1.97Tokens / task: 36,562Steps / task: 85
Cost / task: $0.44Tokens / task: 13,798Steps / task: 21
Cost / task: $2.73Tokens / task: 14,493Steps / task: 42
- #47Muse Spark 1.3medium31.3%
—
Cost / task: $1.75Tokens / task: 32,034Steps / task: 77
Cost / task: $1.97Tokens / task: 10,554Steps / task: 34
Cost / task: $0.080Tokens / task: 23,673Steps / task: 27
- #50Muse Spark 1.3low27.5%
—
Cost / task: $1.13Tokens / task: 20,673Steps / task: 58
Cost / task: $0.28Tokens / task: 10,497Steps / task: 22
Cost / task: $0.98Tokens / task: 5,206Steps / task: 22
- #53Muse Spark 1.3minimal21.3%
—
Cost / task: $0.69Tokens / task: 12,789Steps / task: 42
| # | Model | Score | Cost / task | Tokens / task | Steps / task |
|---|---|---|---|---|---|
Gemini 4 Neonxhigh | 65.4% | $10.67 | 136,273 | 73 | |
| 2 | Gemini 4 Neonhigh | 63.7% | $6.54 | 88,596 | 56 |
| 3 | Gemini 4 Carbonhigh | 61.5% | $8.52 | 114,518 | 97 |
| 4 | Gemini 4 Hydrogenxhigh | 61.4% | $8.09 | 205,981 | 113 |
| 5 | Fable 5.2max Anthropic | 61.3% | $48.11 | 541,003 | 295 |
| 6 | Gemini 4 Carbonmedium | 60.4% | $7.22 | 103,189 | 83 |
| 7 | Fable 5.2xhigh Anthropic | 58.8% | $17.84 | 194,918 | 122 |
| 8 | Opus 5.5max Anthropic | 58.1% | $11.88 | 213,070 | 144 |
| 9 | Gemini 4 Neonmedium | 57.7% | $3.07 | 47,059 | 41 |
| 10 | Gemini 4 Hydrogenhigh | 57.3% | $4.57 | 113,807 | 77 |
| 11 | Opus 5.5xhigh Anthropic | 56.7% | $6.54 | 104,901 | 95 |
| 12 | Fable 5.2high Anthropic | 56.5% | $10.51 | 108,213 | 77 |
| 13 | Gemini 4 Argonhigh | 56.5% | $9.14 | 135,038 | 118 |
| 14 | Gemini 4 Argonmedium | 55.8% | $7.64 | 128,231 | 101 |
| 15 | Gemini 4 Carbonlow | 55.0% | $8.64 | 48,526 | 127 |
| 16 | Opus 5.5high Anthropic | 54.5% | $3.87 | 56,162 | 64 |
| 17 | Sonnet 5.5max Anthropic | 54.4% | $8.63 | 342,273 | 199 |
| 18 | Fable 5.2medium Anthropic | 54.2% | $5.01 | 47,678 | 40 |
| 19 | Fable 5.2low Anthropic | 53.4% | $4.26 | 40,384 | 34 |
| 20 | Opus 5.5medium Anthropic | 50.0% | $2.85 | 39,736 | 52 |
| 21 | Sonnet 5.5xhigh Anthropic | 49.9% | $3.13 | 112,299 | 87 |
| 22 | Grok 4.7xhigh SpaceXSI | 48.6% | $10.19 | 90,268 | 110 |
| 23 | Haiku 5.5max Anthropic | 48.4% | $1.14 | 344,890 | 166 |
| 24 | Gemini 4 Argonlow — | 47.9% | $7.96 | 40,541 | 121 |
| 25 | Gemini 4 Hydrogenmedium | 46.4% | $1.28 | 43,606 | 45 |
| 26 | Grok 4.7high SpaceXSI | 46.0% | $6.88 | 65,850 | 84 |
| 27 | Gemini 4 Neonlow | 45.5% | $1.26 | 19,580 | 26 |
| 28 | Haiku 5.5xhigh Anthropic | 45.2% | $0.56 | 149,314 | 94 |
| 29 | Grok 4.6xhigh SpaceXSI | 44.3% | $5.26 | 58,554 | 62 |
| 30 | Sonnet 5.5high Anthropic | 43.8% | $1.41 | 43,088 | 48 |
| 31 | Opus 5.5low Anthropic | 42.7% | $1.43 | 19,497 | 32 |
| 32 | Grok 4.7medium — | 42.5% | $5.52 | 41,173 | 70 |
| 33 | Muse Spark 1.3max Meta | 41.9% | $2.89 | 56,572 | 113 |
| 34 | Grok 4.6high SpaceXSI | 41.3% | $4.28 | 46,330 | 52 |
| 35 | GPT-5.6 Solmax OpenAI | 40.9% | $7.60 | 40,466 | 100 |
| 36 | Grok 4.6medium SpaceXSI | 38.9% | $2.59 | 26,374 | 40 |
| 37 | Haiku 5.5high Anthropic | 37.5% | $0.31 | 77,196 | 61 |
| 38 | GPT-5.6 Solxhigh OpenAI | 37.4% | $4.32 | 23,921 | 58 |
| 39 | Muse Spark 1.3xhigh Meta | 34.6% | $2.33 | 47,142 | 96 |
| 40 | Sonnet 5.5medium Anthropic | 34.3% | $0.63 | 19,144 | 26 |
| 41 | Haiku 5.5medium Anthropic | 34.2% | $0.17 | 43,441 | 41 |
| 42 | GPT-5.6 Solhigh OpenAI | 33.2% | $3 | 16,319 | 44 |
| 43 | Grok 4.6low SpaceXSI | 33.1% | $1.76 | 16,863 | 33 |
| 44 | Muse Spark 1.3high — | 32.1% | $1.97 | 36,562 | 85 |
| 45 | Sonnet 5.5low Anthropic | 31.8% | $0.44 | 13,798 | 21 |
| 46 | Grok 4.7low SpaceXSI | 31.5% | $2.73 | 14,493 | 42 |
| 47 | Muse Spark 1.3medium — | 31.3% | $1.75 | 32,034 | 77 |
| 48 | GPT-5.6 Solmedium OpenAI | 28.7% | $1.97 | 10,554 | 34 |
| 49 | Haiku 5.5low Anthropic | 27.8% | $0.080 | 23,673 | 27 |
| 50 | Muse Spark 1.3low — | 27.5% | $1.13 | 20,673 | 58 |
| 51 | Gemini 4 Hydrogenlow | 23.9% | $0.28 | 10,497 | 22 |
| 52 | GPT-5.6 Sollow OpenAI | 23.0% | $0.98 | 5,206 | 22 |
| 53 | Muse Spark 1.3minimal — | 21.3% | $0.69 | 12,789 | 42 |
Method and versions
CursorBench is Cursor's in-house benchmark: agents solve ambiguous tasks spanning several files, drawn from real Cursor user sessions. BenchSift shows Cursor's public table as published, without recomputing it.
- Tasks come from real Cursor sessions; Cursor does not publish the task set.
- Each model is evaluated at one or more reasoning levels (Low to Max), each on its own row.
- Cost, tokens and steps are per-task averages Cursor publishes.
- A configuration is tied to a catalogue page by its model name and reasoning level; without a matching page it keeps Cursor's name.
- Cursor designs both the benchmark and the agent that runs it: results reflect its own environment.
Data via Cursor, CursorBench 4.1.