#1
84value index
Price
$4.50blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
83quality signal
ArenaArtificial Analysis
Thoughts on AI, technology, and the future we're building.
New posts every week
Thoughts on AI, technology, and the future we're building.
New posts every week
A focused view of which frontier models deliver the strongest benchmark signal for the money, balancing quality, blended token price, latency, and output speed.
Ranked models
87
Require quality and price matches
Best value
Gemini 3 Pro
84 value index
Lowest price
$0.063
Granite 4.1 8b
Fastest TTFT
0.38s
Granite 4.1 8b
Value formula
The value index normalizes each available signal before blending benchmark quality, blended price, time to first token, and output speed. It avoids raw score-per-dollar math, which can wildly overstate very cheap models.
Higher value index is better. Missing source rows are omitted from the value ranking rather than treated as zero.
Top 30 of 87
| Rank | Model | Index | Price | Latency | Speed | Quality | Sources |
|---|---|---|---|---|---|---|---|
| #1 | 84value index | $4.50blended / 1M tokens | Not listedtime to first token | Not listedoutput speed | 83quality signal | ArenaArtificial Analysis | |
| #2 | 79value index | $10.94blended / 1M tokens | 11.0stime to first token | 47 tok/soutput speed | 98quality signal | ArenaArtificial Analysis | |
| #3 | 79value index | $0.590blended / 1M tokens | 1.33stime to first token | 54 tok/soutput speed | 79quality signal | ArenaArtificial Analysis | |
| #4 | 79value index | $10.94blended / 1M tokens | 1.14stime to first token | 42 tok/soutput speed | 96quality signal | ArenaArtificial Analysis | |
| #5 | 78value index | $3.38blended / 1M tokens | 12.4stime to first token | 198 tok/soutput speed | 80quality signal | ArenaArtificial Analysis | |
| #6 | 78value index | $2.15blended / 1M tokens | 1.12stime to first token | 49 tok/soutput speed | 80quality signal | ArenaArtificial Analysis | |
| #7 | 78value index | $10.94blended / 1M tokens | 1.49stime to first token | 42 tok/soutput speed | 95quality signal | ArenaArtificial Analysis | |
| #8 | 77value index | $4.50blended / 1M tokens | 22.5stime to first token | 120 tok/soutput speed | 82quality signal | ArenaArtificial Analysis | |
| #9 | 75value index | $1.71blended / 1M tokens | 1.34stime to first token | 42 tok/soutput speed | 74quality signal | ArenaArtificial Analysis | |
| #10 | 74value index | $6.56blended / 1M tokens | 1.13stime to first token | 47 tok/soutput speed | 80quality signal | ArenaArtificial Analysis | |
| #11 | 73value index | $3.75blended / 1M tokens | 1.75stime to first token | 179 tok/soutput speed | 70quality signal | ArenaArtificial Analysis | |
| #12 | 73value index | $11.25blended / 1M tokens | Not listedtime to first token | Not listedoutput speed | 77quality signal | ArenaArtificial Analysis | |
| #13 | 73value index | $1.35blended / 1M tokens | 2.47stime to first token | 46 tok/soutput speed | 69quality signal | ArenaArtificial Analysis | |
| #14 | 72value index | $1.13blended / 1M tokens | 0.93stime to first token | 184 tok/soutput speed | 65quality signal | ArenaArtificial Analysis | |
| #15 | 72value index | $0.525blended / 1M tokens | 2.35stime to first token | 179 tok/soutput speed | 63quality signal | ArenaArtificial Analysis | |
| #16 | 71value index | $0.525blended / 1M tokens | 2.34stime to first token | 202 tok/soutput speed | 61quality signal | ArenaArtificial Analysis | |
| #17 | 71value index | $1.56blended / 1M tokens | 0.60stime to first token | 127 tok/soutput speed | 64quality signal | ArenaArtificial Analysis | |
| #18 | 71value index | $0.544blended / 1M tokens | 1.05stime to first token | 45 tok/soutput speed | 64quality signal | ArenaArtificial Analysis | |
| #19 | 71value index | $11.25blended / 1M tokens | 17.1stime to first token | 61 tok/soutput speed | 82quality signal | ArenaArtificial Analysis | |
| #20 | 70value index | $2.93blended / 1M tokens | 1.89stime to first token | 41 tok/soutput speed | 66quality signal | ArenaArtificial Analysis | |
| #21 | 70value index | $11.25blended / 1M tokens | 0.88stime to first token | 51 tok/soutput speed | 79quality signal | ArenaArtificial Analysis | |
| #22 | 69value index | $1.69blended / 1M tokens | 8.48stime to first token | 163 tok/soutput speed | 61quality signal | ArenaArtificial Analysis | |
| #23 | 69value index | $1.55blended / 1M tokens | 0.81stime to first token | 80 tok/soutput speed | 61quality signal | ArenaArtificial Analysis | |
| #24 | 69value index | $1.19blended / 1M tokens | 1.34stime to first token | 33 tok/soutput speed | 61quality signal | ArenaArtificial Analysis | |
| #25 | 68value index | $0.825blended / 1M tokens | 1.38stime to first token | 83 tok/soutput speed | 59quality signal | ArenaArtificial Analysis | |
| #26 | 67value index | $3.44blended / 1M tokens | 41.3stime to first token | 86 tok/soutput speed | 64quality signal | ArenaArtificial Analysis | |
| #27 | 66value index | $1.35blended / 1M tokens | 1.83stime to first token | 52 tok/soutput speed | 56quality signal | ArenaArtificial Analysis | |
| #28 | 66value index | $0.175blended / 1M tokens | 2.12stime to first token | 78 tok/soutput speed | 53quality signal | ArenaArtificial Analysis | |
| #29 | 66value index | $1.13blended / 1M tokens | 1.89stime to first token | 53 tok/soutput speed | 55quality signal | ArenaArtificial Analysis | |
| #30 | 66value index | $0.463blended / 1M tokens | 3.50stime to first token | 160 tok/soutput speed | 52quality signal | ArenaArtificial Analysis |
Benchmark guide
A quick reading key for interpreting the value rankings without over-weighting one benchmark, price point, or speed measurement.
The value index blends normalized benchmark quality, blended token price, latency, and output speed. It is designed to answer which models deliver strong public performance for the money, not which model is best in every task.
Raw score-per-dollar can exaggerate extremely cheap models and make small benchmark differences look larger than they are. Normalizing each signal keeps the ranking easier to compare across quality, price, and speed.
A model needs both a benchmark quality signal and a confident price match to be ranked. If the price or benchmark source is missing, the model is omitted rather than treated as free or zero quality.
Price estimates cost, latency measures time to first token, and speed measures output throughput after generation begins. The best model for a product depends on which constraint matters most in the actual workflow.