Part of Best LLM for Chat & Roleplay
Best LLM for Roleplay & Character
Gemini 3.8 Flash ranks first for Roleplay & Character as of November 14, 2026.[1][2] It scores 81.41% on LiveBench Instruction Following (#1 of 59), including paraphrasing, simplifying, story generation, and summarization. Gemini 3.7 Flash is the next-ranked alternative. It scores 79.93% on LiveBench Instruction Following (#2 of 59), including paraphrasing, simplifying, story generation, and summarization.
- Best non-Google pick: Muse Spark 1.3 (#4)
- Compare Gemini 3.8 Flash vs Gemini 3.7 Flash →
About this recommendation
- Updated
- Evidence through
- Sources
- 13
- Revision
- v117
Decision audit
Why this result
Inspect the inputs and the computed order behind the recommendation.
Models screened
24
live candidates
Evaluation feeds
4
task-weighted
Winner coverage
100%
intended feed weight
Largest provider share
5 of 8
Google: Gemini 3.8 Flash leads the measured task comparison with 2 independent evaluation families. Community volume, release age and usage popularity add no ranking points.
Real-world track record is still developing. The recommendation can lead on independent measurements while practitioner reports accumulate.
Sources evaluated
These are the weights used in scoring. Missing measurements are omitted from each model’s average. A feed with no result for any model released in the last 60 days is stale and does not score until it catches up.
| Evaluation feed | Weight | Winner result | Field measured |
|---|---|---|---|
| LMArena Creative WritingObserved 2026-11-11 · evaluation date not supplied · high effort | 39% | #9 | 24/24 |
| LMArena TextObserved 2026-11-11 · evaluation date not supplied · high effort | 28% | #9 | 23/24 |
| LiveBench Instruction Following (2026-06-25)Observed 2026-10-18 · evaluation date not supplied · gemini-3.8-flash-highfailing; last successful check 2026-10-18 | 22% | #1 | 24/24 |
| LiveBench Language (2026-06-25)Observed 2026-10-18 · evaluation date not supplied · gemini-3.8-flash-highfailing; last successful check 2026-10-18 | 11% | #6 | 24/24 |
Provider concentration
Each exact model is scored separately; provider identity is not a ranking input.
- Google5 models
- Anthropic1 model
- Meta1 model
- OpenAI1 model
Decision table
Every published model is shown in computed order. Practitioner sources are distinct community threads, not the citations repeated in the prose below.
Google · coverage 100%
#1 LiveBench Instruction Following · #6 LiveBench Language
Google · coverage 100%
#2 LiveBench Instruction Following · #11 LiveBench Language
Google · coverage 100%
#3 LiveBench Instruction Following · #12 LiveBench Language
Meta · coverage 100%
#4 LiveBench Instruction Following · #9 LMArena Text
Google · coverage 100%
#6 LiveBench Instruction Following · #14 LiveBench Language
Anthropic · coverage 100%
#3 LMArena Creative Writing · #4 LMArena Text
Google · coverage 72%
#8 LiveBench Instruction Following · #15 LiveBench Language
OpenAI · coverage 100%
#4 LiveBench Language · #7 LiveBench Instruction Following
Task score averages the available, task-weighted measurements. Benchmark positions compare models matched to our catalog. Models measured by at least two independent evaluator families are considered first. Missing tests, practitioner report counts, popularity and release age add no points. Coverage describes evidence breadth, not a probability of correctness. Scores within two points are shown as close under this policy; this is not a statistical confidence interval. When the leading scores are that close, the model measured by more evaluator families ranks first.
- 01
Gemini 3.8 FlashGoogle · $0.83 in / $4.13 out per M tokens · 1.0M context
Gemini 3.8 Flash scores 81.41% on LiveBench Instruction Following (#1 of 59), including paraphrasing, simplifying, story generation, and summarization.
Best when: Its strongest result for this task is on LiveBench Instruction Following, which measures following detailed instructions exactly.No practitioner reports are linked yet, so no cautions are listed. Absence of reports is not evidence of reliability.
- 02
Gemini 3.7 FlashGoogle · $0.75 in / $3.75 out per M tokens · 1.0M context
Gemini 3.7 Flash scores 79.93% on LiveBench Instruction Following (#2 of 59), including paraphrasing, simplifying, story generation, and summarization.
Best when: Its strongest result for this task is on LiveBench Instruction Following, which measures following detailed instructions exactly.No practitioner reports are linked yet, so no cautions are listed. Absence of reports is not evidence of reliability.
- 03
Gemini 3.1 Pro PreviewGoogle · $2 in / $12 out per M tokens · 1.0M context
Gemini 3.1 Pro Preview scores 79.1% on LiveBench Instruction Following (#3 of 59), including paraphrasing, simplifying, story generation, and summarization.
Best when: Its strongest result for this task is on LiveBench Instruction Following, which measures following detailed instructions exactly.No practitioner reports are linked yet, so no cautions are listed. Absence of reports is not evidence of reliability.
- 04
Muse Spark 1.3Meta · $1.25 in / $4.25 out per M tokens · 1.0M context
Muse Spark 1.3 ties for #9 on LMArena's overall text arena (Elo 1497) but drops to #16 on creative-writing (Elo 1467), showing stronger general than creative-specific preference.
Best when: Its strongest result for this task is on LiveBench Instruction Following, which measures following detailed instructions exactly.Watch out for
- Expect weaker creative-writing specific performance relative to its overall ranking, as its creative-writing Elo (1467) trails 30 points behind its overall score.
- 05
Gemini 3.5 FlashGoogle · $1.50 in / $9 out per M tokens · 1.0M context
Gemini 3.5 Flash scores 75.6% on LiveBench Instruction Following (#6 of 59), including paraphrasing, simplifying, story generation, and summarization.
Best when: Its strongest result for this task is on LiveBench Instruction Following, which measures following detailed instructions exactly.No practitioner reports are linked yet, so no cautions are listed. Absence of reports is not evidence of reliability.
- 06
Claude Opus 5.5Anthropic · $4 in / $20 out per M tokens · 1M context
Claude Opus 5.5 ranks #3 on LMArena's creative-writing category with an Elo of 1532, the highest creative-writing score in this pool.
Best when: Its strongest result for this task is on LMArena Creative Writing, which measures creative writing people prefer in blind comparison.Watch out for
- Watch for instruction-following gaps in structured story generation, as it ranks #34 on LiveBench Instruction Following with 65.74%.
- 07
Gemini 3.6 FlashGoogle · $0.75 in / $3.75 out per M tokens · 1.0M context
Gemini 3.6 Flash scores 75.37% on LiveBench Instruction Following (#8 of 59), including paraphrasing, simplifying, story generation, and summarization.
Best when: Its strongest result for this task is on LiveBench Instruction Following, which measures following detailed instructions exactly.No practitioner reports are linked yet, so no cautions are listed. Absence of reports is not evidence of reliability.
- 08
GPT-6 AstraOpenAI · $10 in / $50 out per M tokens · 1.1M context
GPT-6 Astra ranks #30 on LMArena's overall text arena (Elo 1474) but plummets to #47 on creative-writing (Elo 1421), despite strong language manipulation at #4 on LiveBench.
Best when: Use for language manipulation subtasks within larger workflows, as it scores 89.43% on LiveBench Language (#4 of 59).Watch out for
- Avoid for creative-writing emphasis, as its 1421 Elo represents a 53-point drop from its overall ranking.
Frequently asked
- What is the best model for Roleplay & Character?
- Gemini 3.8 Flash ranks first as of November 14, 2026. Gemini 3.8 Flash scores 81.41% on LiveBench Instruction Following (#1 of 59), including paraphrasing, simplifying, story generation, and summarization.[1]
- What is the best alternative to Gemini 3.8 Flash?
- Gemini 3.7 Flash ranks second. Gemini 3.7 Flash scores 79.93% on LiveBench Instruction Following (#2 of 59), including paraphrasing, simplifying, story generation, and summarization.[2]
Sources
- 1
“Within the 59 catalog models matched to this evaluation: Scores 81.41% on LiveBench Instruction Following (#1 of 59), including paraphrasing, simplifying, story generation, and summarization.”
LiveBench Instruction Following · Benchmark · Oct 18, 2026 - 2
“Within the 59 catalog models matched to this evaluation: Scores 79.93% on LiveBench Instruction Following (#2 of 59), including paraphrasing, simplifying, story generation, and summarization.”
LiveBench Instruction Following · Benchmark · Oct 18, 2026 - 3
“Within the 59 catalog models matched to this evaluation: Scores 79.1% on LiveBench Instruction Following (#3 of 59), including paraphrasing, simplifying, story generation, and summarization.”
LiveBench Instruction Following · Benchmark · Oct 18, 2026 - 4
“Within the 59 catalog models matched to this evaluation: Scores 78% on LiveBench Instruction Following (#4 of 59), including paraphrasing, simplifying, story generation, and summarization.”
LiveBench Instruction Following · Benchmark · Oct 18, 2026 - 5
“Within the 148 catalog models matched to this evaluation: Ranks #16 of 148 on LMArena's creative-writing category (Elo 1467), based on blind human preference votes.”
LMArena creative-writing category · Benchmark · Nov 11, 2026 - 6
“Within the 147 catalog models matched to this evaluation: Ranks #9 of 147 on LMArena's overall text arena (Elo 1497), based on blind human preference votes.”
LMArena text arena · Benchmark · Nov 11, 2026 - 7
“Within the 59 catalog models matched to this evaluation: Scores 75.6% on LiveBench Instruction Following (#6 of 59), including paraphrasing, simplifying, story generation, and summarization.”
LiveBench Instruction Following · Benchmark · Oct 18, 2026 - 8
“Within the 148 catalog models matched to this evaluation: Ranks #3 of 148 on LMArena's creative-writing category (Elo 1532), based on blind human preference votes.”
LMArena creative-writing category · Benchmark · Nov 11, 2026 - 9
“Within the 59 catalog models matched to this evaluation: Scores 65.74% on LiveBench Instruction Following (#34 of 59), including paraphrasing, simplifying, story generation, and summarization.”
LiveBench Instruction Following · Benchmark · Oct 18, 2026 - 10
“Within the 59 catalog models matched to this evaluation: Scores 75.37% on LiveBench Instruction Following (#8 of 59), including paraphrasing, simplifying, story generation, and summarization.”
LiveBench Instruction Following · Benchmark · Oct 18, 2026 - 11
“Within the 59 catalog models matched to this evaluation: Scores 89.43% on LiveBench Language (#4 of 59), an objective evaluation of language manipulation tasks.”
LiveBench Language · Benchmark · Oct 18, 2026 - 12
“Within the 148 catalog models matched to this evaluation: Ranks #47 of 148 on LMArena's creative-writing category (Elo 1421), based on blind human preference votes.”
LMArena creative-writing category · Benchmark · Nov 11, 2026 - 13
“Within the 147 catalog models matched to this evaluation: Ranks #30 of 147 on LMArena's overall text arena (Elo 1474), based on blind human preference votes.”
LMArena text arena · Benchmark · Nov 11, 2026
Rankings synthesized from community evidence and open benchmarks. See methodology. Not driven by vendor marketing.