Across 4 comparable benchmarks, Gemini 4 Neon has better reported results on 4 and worse on 0. 1 further shared result is listed below, each with the reason it is not counted.
Moderate evidence4 of 5 shared results countedHow we compare
Price basis: Standard rates. The price section below shows the applicable periods.
| Fact | Mercury 3 | Gemini 4 Neon |
|---|---|---|
| Context window | 1M tokens | 1M tokens |
| Input / 1M | $0.100 | $3.00 |
| Output / 1M | $0.350 | $15.00 |
| Blended (4:1) | $0.085 | $3.35 |
| Status | Available | Available |
| Released | October 19, 2026 | November 18, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 2 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Gemini 4 Neon ahead on 1 of 1 counted
Gemini 4 Neon ahead on 2 of 2 counted
No shared comparable results for Abstract reasoning, Mathematics, Science & health, Computer & tool use, Research & search, Long context, Multimodal, Cybersecurity.
Published scores, with matching modes where available. Gaps show Mercury 3 relative to Gemini 4 Neon. Reading the results
| Benchmark | Mercury 3 | Gemini 4 Neon | 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 | 63.6≠Extra-High · tools· legacy-default | —#70 vs #7 of 90 |
| Vibe Code Bench v1.1Code Generation & Editing · Pass rate (%) | 60.9Thinking High · tools | 93.7≠Extra-High · tools | −32.8 pts#59 vs #2 of 121 |
| Legal Research BenchLegal · Score | 28.9Thinking High · tools | 56.3≠Extra-High · tools + internet | 0.51×#58 vs #1 of 91 |
| Tax Agent BenchFinance · Accuracy (%, rubric × citation quality) | 18.2Thinking High · tools | 54.9≠Extra-High · tools + internet | −36.7 pts#56 vs #22 of 74 |
| Vals Index v2.2Capability Indices · GDP-weighted accuracy (%) | 43.7Thinking High · tools | 70.9≠Extra-High · tools | −27.2 pts#32 vs #2 of 36 |
Agentic Development · Resolution rate (%)
Not counted · Different or unrecorded test environments — excluded from the tally
Code Generation & Editing · Pass rate (%)
Legal · Score
Finance · Accuracy (%, rubric × citation quality)
Capability Indices · GDP-weighted accuracy (%)
A dash means no result is available.
| Benchmark | Mercury 3 | Gemini 4 Neon |
|---|---|---|
| HLE-Diamond | — | 71.3 |
| MysteryMechanism | — | 45.0 |
| Terminal-Bench-Science 0.1 | — | 70.0 |
| AA Coding Agent Index v2.0 | — | 58.6 |
| FrontierCode 2.0 | — | 46.2 |
| SWE-sweep | — | 12.8 |
| Terminal-Bench 4.1 | — | 65.2 |
| AutomationBench-AA | — | 79.3 |
| SEC-Bench Pro | — | 90.5 |
| AA Intelligence Index v5.0.1 | — | 61.4 |
| Agent Arena Index | — | 1333 |
| Chartography | — | 73.5 |
| GDP.pdf | — | 33.4 |
| LVBench | — | 89.0 |
| AA-Briefcase | — | 1700 |
| AutomationBench | — | 56.3 |
| SimpleBench | — | 94.4 |
| Vending-Bench 2 | — | 16843 |
| AA-Omniscience | — | 54.8 |
| BioMysteryBench | — | 80.0 |
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 costs97%lessthan Gemini 4 Neon per million tokens — 39.3× cheaper.Using standard 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
Gemini 4 Neon: Standard pricing. Unified 1M context pricing; thinking tokens included in output; paid tier only (no free tier).
| Price / 1M tokens | Mercury 3 | Gemini 4 Neon | Ratio |
|---|---|---|---|
| Input | $0.10 | $3.00 | 0.03× |
| Output | $0.35 | $15.00 | 0.02× |
| Cached input | $0.01 | $0.15 | 0.07× |
| Cache write | — | — | — |
| Blended | $0.085 | $3.35 | 0.03× |
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.
Mercury 3 relative to Gemini 4 Neon
No matching recorded settings for a cost summary.
Summary: 0 of 4 shared benchmarks have matching recorded settings and sources. The average is a geometric mean of 0 positive-cost ratios, one equal weight per benchmark. This benchmark set can include related tests and indexes; it is not a workload cost estimate.
Settings or sources differ
Settings or sources differ
Settings or sources differ
Settings or sources differ
Settings or sources differ
Settings or sources differ
Settings or sources differ
Settings or sources differ
Settings or sources differ or are not recorded; interpret the comparison with care.
Mercury 3
Gemini 4 Neon
Settings or sources differ or are not recorded; interpret the comparison with care.
Mercury 3
Gemini 4 Neon
Settings or sources differ or are not recorded; interpret the comparison with care.
Mercury 3
Gemini 4 Neon
Settings or sources differ or are not recorded; interpret the comparison with care.
Mercury 3
Gemini 4 Neon
| Benchmark | Mercury 3 | Gemini 4 Neon |
|---|---|---|
| AA Coding Agent Index v2.0 | Not reported | |
| AA Intelligence Index v5.0.1 | Not reported | 1 more settings |
| Agent Arena Index | Not reported | $2.5996 / task Median · Agent Arena Index rating (index points): 1333 Thinking High (With Tools + Internet) |
| Terminal-Bench 4.0 | $0.42 / task Average · Resolution rate (%): 3.0 Unspecified Reasoning (With Tools) · vals-mini-swe | Not reported |
| Attribute | Mercury 3 | Gemini 4 Neon |
|---|---|---|
| Availability | Available | Available |
| Provider | Inception Labs | Google Deep Mind |
| Model type | Reasoning model | Multimodal model |
| First release | October 19, 2026 | November 18, 2026 |
| Context window | 1M tokens | 1M tokens |
| Max output | 128K tokens | 1M tokens |
| Architecture | Undisclosed | Undisclosed |
| Documented capabilities | Reasoning, Tool use, Function calling, Structured output, Long context, Coding | Reasoning, Coding, Tool use, Computer use, Long context, Function calling, Structured output, Web search |
| Knowledge cutoff | — | 2026-03 |
| Input modalities | Text | Text, Image, Audio, Video |
| 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 Gemini 4 Neon? 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.