Across 1 comparable benchmark, GPT-6.2 Sol has better reported results on 1 and worse on 0. 1 further shared result is listed below, each with the reason it is not counted.
Limited evidence1 of 2 shared results countedHow we compare
Price basis: Standard rates vs listed rates. The price section below shows the applicable periods.
| Fact | Mercury 3 | GPT-6.2 Sol |
|---|---|---|
| Context window | 1M tokens | 1.05M tokens |
| Input / 1M | $0.100 | $2.00 |
| Output / 1M | $0.350 | $10.00 |
| Blended (4:1) | $0.085 | $2.23 |
| Status | Available | Available |
| Released | October 19, 2026 | November 17, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Published scores, with matching modes where available. Gaps show Mercury 3 relative to GPT-6.2 Sol. Reading the results
| Benchmark | Mercury 3 | GPT-6.2 Sol | Gap |
|---|---|---|---|
| Terminal-Bench 4.0Agentic Development · Resolution rate (%)Not counted · Different or unrecorded test environments — excluded from the tally | 3.0Unspecified Reasoning · tools· vals-mini-swe | 60.1≠Max · tools· legacy-default | —#70 vs #10 of 90 |
| Vals Index v2.2Capability Indices · GDP-weighted accuracy (%) | 43.7Thinking High · tools | 66.1≠Max · task tools | −22.4 pts#32 vs #9 of 36 |
Agentic Development · Resolution rate (%)
Not counted · Different or unrecorded test environments — excluded from the tally
Capability Indices · GDP-weighted accuracy (%)
A dash means no result is available.
| Benchmark | Mercury 3 | GPT-6.2 Sol |
|---|---|---|
| GPQA Diamond | — | 96.0 |
| HLE-Diamond | — | 64.0 |
| Terminal-Bench-Science 0.1 | — | 67.6 |
| FrontierCode 2.0 | — | 44.4 |
| SWE-sweep | — | 11.6 |
| Terminal-Bench 4.1 | — | 61.5 |
| Vibe Code Bench v1.1 | 60.9 | — |
| SEC-Bench Pro | — | 88.3 |
| AA Intelligence Index v5.0.1 | — | 57.3 |
| Agent Arena Index | — | 1241 |
| Chartography | — | 75.1 |
| GDP.pdf | — | 30.0 |
| LVBench | — | 87.6 |
| AA-AnalystAgent | — | 53.8 |
| AutomationBench | — | 41.3 |
| BenchCAD 2.1 Core | — | 73.1 |
| Harvey LAB-AA v1.1 (All-pass) | — | 11.1 |
| Legal Research Bench | 28.9 | — |
| Tax Agent Bench | 18.2 | — |
| SimpleBench | — | 69.9 |
| HealthBench Professional | — | 65.9 |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
Mercury 3 costs96%lessthan GPT-6.2 Sol per million tokens — 26.2× cheaper.Using standard rates vs listed rates at this token mix.
Mercury 3: Standard pricing. Inception Labs official docs/get-started/models.md verified 2026-11-13 (50% promo pricing prior to 2026-12-28 wind-down); Mercury 3 with 50% cache read promo
GPT-6.2 Sol: Standard pricing. context_length <= 272000 Official OpenAI per-million-token pricing. Full request uses the applicable input-token band. context_length > 272000
| Price / 1M tokens | Mercury 3 | GPT-6.2 Sol | Ratio |
|---|---|---|---|
| Input | $0.10 | $2.00 | 0.05× |
| Output | $0.35 | $10.00 | 0.03× |
| Cached input | $0.01 | $0.10 | 0.10× |
| Cache write | — | $2.50 | — |
| Blended | $0.085 | $2.23 | 0.04× |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
| Benchmark | Mercury 3 | GPT-6.2 Sol |
|---|---|---|
| AA Intelligence Index v5.0.1 | Not reported | 2 more settings |
| Agent Arena Index | Not reported | $0.9817 / task Median · Agent Arena Index rating (index points): 1241 Max (With Tools + Internet) |
| BenchCAD 2.1 Core | Not reported | $0.75 / task Average · Core mean geometry/circuit score (0–100): 64.0 Thinking High (With Tools) $0.15 / task Average · Core mean geometry/circuit score (0–100): 23.9 Thinking Low (With Tools) 2 more settings$0.29 / task Average · Core mean geometry/circuit score (0–100): 41.2 Thinking Medium (With Tools) $1.00 / task Average · Core mean geometry/circuit score (0–100): 70.4 Extra-High (With Tools) |
| FrontierCode 2.0 | Not reported | $0.876 / task Average · Weighted rubric score: 39.7 Thinking High (With Tools + Internet) 2 more settings$0.685 / task Average · Weighted rubric score: 38.3 Thinking Medium (With Tools + Internet) |
| Legal Research Bench | Not reported | |
| Tax Agent Bench | $0.0459 / task Average · Accuracy (%, rubric × citation quality): 18.2 Thinking High (With Tools) | Not reported |
| Terminal-Bench 4.0 | $0.42 / task Average · Resolution rate (%): 3.0 Unspecified Reasoning (With Tools) · vals-mini-swe | Not reported |
| Vals Index v2.2 | Not reported | |
| Vibe Code Bench v1.1 | Not reported |
| Attribute | Mercury 3 | GPT-6.2 Sol |
|---|---|---|
| Availability | Available | Available |
| Provider | Inception Labs | OpenAI |
| Model type | Reasoning model | Reasoning model |
| First release | October 19, 2026 | November 17, 2026 |
| Context window | 1M tokens | 1.05M tokens |
| Max output | 128K tokens | 128K tokens |
| Architecture | Undisclosed | Undisclosed |
| Documented capabilities | Reasoning, Tool use, Function calling, Structured output, Long context, Coding | Reasoning, Coding, Function calling, Tool use, Structured output, Computer use, Web search, Long context |
| Knowledge cutoff | — | 2026-06-01 |
| Input modalities | Text | Text, Image |
| Output modalities | Text | Text |
| Weights | Closed / API only | Closed / API only |
| Commercial use | Proprietary | Proprietary |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used Mercury 3 or GPT-6.2 Sol? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.